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

    Neuronpedia

    INDEX
    Explanations

    terms related to development and progress

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iff
    -0.17
     lẽ
    -0.15
    fait
    -0.15
    ansen
    -0.14
    yt
    -0.14
    ball
    -0.14
    dre
    -0.14
    ners
    -0.14
    bestos
    -0.14
    pell
    -0.14
    POSITIVE LOGITS
    PMENT
    0.22
    ped
    0.19
    ally
    0.19
    票
    0.18
    mental
    0.17
    lop
    0.16
    velopment
    0.16
    olver
    0.16
    ement
    0.15
    oted
    0.15
    Act Density 0.073%

    No Known Activations