Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    various attitudes and behaviors, particularly those related to policies, contributions, and antagonism in social contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    followed by "towards" or "toward"

    np_acts-logits-general · gemini-2.0-flash

    expressing direction towards

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SequentialGroup
    -0.65
    NameInMap
    -0.60
     Joplin
    -0.57
     Wern
    -0.56
    ///</
    -0.55
     HasFactory
    -0.54
    hugh
    -0.53
     KTP
    -0.52
     Aftermath
    -0.49
     Vessel
    -0.48
    POSITIVE LOGITS
     towards
    3.12
     toward
    2.99
    towards
    2.65
    toward
    2.57
     Towards
    2.53
     Toward
    2.40
    Towards
    2.30
    Toward
    2.11
     hacia
    1.98
     TOW
    1.79
    Act Density 0.506%

    No Known Activations