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

    Neuronpedia

    INDEX
    Explanations

    references to paper and paper-related products

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    spark
    -0.20
    sb
    -0.19
    eva
    -0.18
    say
    -0.17
    sin
    -0.17
    ĽĪ
    -0.17
    yw
    -0.17
    yre
    -0.16
    entifier
    -0.16
    special
    -0.15
    POSITIVE LOGITS
    clip
    0.36
    backs
    0.32
    weight
    0.29
    weights
    0.28
     towel
    0.25
    trail
    0.25
    less
    0.25
    .li
    0.25
    board
    0.24
    doll
    0.24
    Act Density 0.026%

    No Known Activations