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

    Neuronpedia

    INDEX
    Explanations

    expressions of belief or conviction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    alent
    -0.16
    _DETECT
    -0.16
    rak
    -0.15
    ĭ
    -0.15
    /on
    -0.15
    yh
    -0.15
    dea
    -0.15
    vik
    -0.14
    ymb
    -0.14
    utz
    -0.14
    POSITIVE LOGITS
     strongly
    0.28
    fully
    0.20
    lessly
    0.20
     firmly
    0.19
     passionately
    0.18
    fulness
    0.17
    ÅĽmy
    0.17
     there
    0.16
     whole
    0.16
    whole
    0.15
    Act Density 0.041%

    No Known Activations