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

    Neuronpedia

    INDEX
    Explanations

    specfic information that is not widely known or understood

    oai_token-act-pair · gpt-3.5-turbo

    instances of awareness or lack of knowledge about something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ŃĶ
    -0.84
    oulos
    -0.79
    Dialogue
    -0.76
    thren
    -0.74
    attery
    -0.71
    ciating
    -0.68
    Dialog
    -0.66
    oubted
    -0.66
    è£ħ
    -0.64
     rall
    -0.64
    POSITIVE LOGITS
     nor
    0.98
     anymore
    0.95
    ledge
    0.92
     until
    0.87
     anything
    0.86
     existed
    0.82
    heit
    0.82
     beforehand
    0.81
     how
    0.78
     till
    0.77
    Act Density 0.122%

    No Known Activations