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

    Neuronpedia

    INDEX
    Explanations

    instances of greeting or conversational transitions

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

    emotional expressions and social interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    UnknownFieldSet
    -0.84
     AssertionError
    -0.80
    AsUp
    -0.76
    -0.71
    Demografie
    -0.68
    NewUrlParser
    -0.67
    AxisAlignment
    -0.67
     الحره
    -0.67
     ivelany
    -0.67
    iastes
    -0.65
    POSITIVE LOGITS
    ↵↵
    0.54
     The
    0.54
     
    0.54
    ↵
    0.49
     very
    0.47
    fortawesome
    0.46
     You
    0.46
     gefallen
    0.45
     Very
    0.44
     We
    0.44
    Act Density 0.351%

    No Known Activations