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

    Neuronpedia

    INDEX
    Explanations

    prepositions and related terms indicating direction or orientation

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

    direction toward a target

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    哔
    -0.40
    ektiv
    -0.38
     kew
    -0.38
    ricanes
    -0.37
    SEGUIR
    -0.37
     frankly
    -0.36
     stumped
    -0.36
    WebVitals
    -0.36
     resell
    -0.36
     taj
    -0.36
    POSITIVE LOGITS
    Toward
    1.48
    Towards
    1.45
     toward
    1.44
     towards
    1.44
     Toward
    1.42
     Towards
    1.41
    towards
    1.39
    toward
    1.39
     hacia
    1.01
    hacia
    0.94
    Act Density 0.028%

    No Known Activations