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

    Neuronpedia

    INDEX
    Explanations

    verbs related to organizing, regulating, and manipulating actions

    oai_token-act-pair · gpt-3.5-turbo

    words related to control, organization, and management of processes or systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ammy
    -0.82
    este
    -0.70
    fare
    -0.69
    founder
    -0.67
    rug
    -0.66
    aver
    -0.66
    eal
    -0.65
    hon
    -0.64
    reading
    -0.64
    alian
    -0.63
    POSITIVE LOGITS
    ments
    1.09
     yourselves
    0.88
     them
    0.81
    ively
    0.78
     oneself
    0.77
    MENTS
    0.75
     yourself
    0.74
    ATIVE
    0.72
     him
    0.72
    uate
    0.71
    Act Density 0.401%

    No Known Activations