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

    Neuronpedia

    INDEX
    Explanations

    words related to being motivated, determined, or influenced by a particular force or desire

    oai_token-act-pair · gpt-3.5-turbo

    the concept of being motivated or compelled by various factors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Canad
    -0.82
    iannopoulos
    -0.74
    assium
    -0.73
    ypes
    -0.72
    enegger
    -0.72
    ITION
    -0.71
     Leilan
    -0.70
    umbn
    -0.70
    yang
    -0.68
    akov
    -0.68
    POSITIVE LOGITS
     driven
    0.98
    driven
    0.86
    driving
    0.80
    vable
    0.79
    uced
    0.71
    ousel
    0.70
     Dri
    0.69
    ministic
    0.69
    active
    0.68
    cks
    0.68
    Act Density 0.026%

    No Known Activations