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

    Neuronpedia

    INDEX
    Explanations

    references to specific quantities or numerical values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    restler
    -0.44
     αὐτ
    -0.42
     CST
    -0.42
     Mulligan
    -0.42
    stück
    -0.40
     Cowell
    -0.40
     necro
    -0.40
     Lowell
    -0.40
     Crucible
    -0.40
    퓌
    -0.39
    POSITIVE LOGITS
     ویکی‌پدی
    0.82
    RegressionTest
    0.76
     ProtoMessage
    0.65
    AndEndTag
    0.64
    writeFieldEnd
    0.62
    دانشنامهٔ
    0.60
    <bos>
    0.59
    ↵↵
    0.59
     мәкал
    0.58
    httphttps
    0.57
    Act Density 0.613%

    No Known Activations