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

    Neuronpedia

    INDEX
    Explanations

    actions related to espionage or surveillance activities

    oai_token-act-pair · gpt-3.5-turbo

    actions and processes related to surveillance and tracking

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     destro
    -0.73
     withd
    -0.71
    utenberg
    -0.68
     notor
    -0.61
     concess
    -0.61
     Monstrous
    -0.60
     Ruins
    -0.59
     exha
    -0.57
    akeru
    -0.56
    DIV
    -0.55
    POSITIVE LOGITS
    ings
    1.45
    able
    1.45
    ables
    1.23
    backs
    1.22
    ability
    1.15
    ingly
    1.10
    fulness
    1.03
    ments
    0.99
    ances
    0.95
    outs
    0.93
    Act Density 0.594%

    No Known Activations