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

    Neuronpedia

    INDEX
    Explanations

    phrases relating to arrival or involvement in a certain place or situation

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to movement and location

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orius
    -0.72
    GY
    -0.70
    %%%%
    -0.67
    PIN
    -0.65
    RT
    -0.58
    Cooldown
    -0.58
    aldi
    -0.56
     Chop
    -0.56
    IAS
    -0.56
    girls
    -0.56
    POSITIVE LOGITS
     unprepared
    1.13
     smelling
    1.12
     expecting
    1.09
     victorious
    1.00
     sidx
    0.98
     wanting
    0.97
     confident
    0.96
     intending
    0.96
     unsc
    0.94
     knowing
    0.91
    Act Density 0.176%

    No Known Activations