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

    Neuronpedia

    INDEX
    Explanations

    references to communal or collective action and inclusion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aisy
    -0.16
     îł
    -0.15
    odb
    -0.15
    sez
    -0.15
     voc
    -0.15
    _utilities
    -0.15
    -hooks
    -0.14
    éĸĢ
    -0.14
    Æ°ng
    -0.14
    rons
    -0.14
    POSITIVE LOGITS
     Invest
    0.16
     invest
    0.15
    hill
    0.14
    athing
    0.14
     investing
    0.14
    amil
    0.14
    Ñıд
    0.13
    rowser
    0.13
     Vim
    0.13
     seeding
    0.13
    Act Density 0.016%

    No Known Activations