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

    Neuronpedia

    INDEX
    Explanations

    elements related to agency and action, particularly emphasizing individuals taking initiatives or exhibiting behaviors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ngr
    -0.16
    orent
    -0.16
    anta
    -0.15
    onal
    -0.15
    uden
    -0.15
    engu
    -0.14
    cord
    -0.14
    acades
    -0.14
    ucha
    -0.14
    icode
    -0.14
    POSITIVE LOGITS
    ock
    0.14
    deo
    0.14
    ane
    0.14
    se
    0.14
     STAT
    0.14
    dom
    0.13
    ubs
    0.13
    ãĥ¼ãĥij
    0.13
     letterSpacing
    0.13
    .Rect
    0.13
    Act Density 0.012%

    No Known Activations