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

    Neuronpedia

    INDEX
    Explanations

    phrases introducing assumptions or conditions in mathematical or logical expressions

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    batore
    -0.88
    AndEndTag
    -0.83
    охра
    -0.82
     مشين
    -0.78
    findpost
    -0.76
    XMLSchema
    -0.73
     sphinx
    -0.73
    AxisSize
    -0.71
     محفوظة
    -0.71
     traseiro
    -0.71
    POSITIVE LOGITS
     Let
    1.13
    Let
    1.12
    let
    1.05
     LET
    1.05
     let
    0.99
    LET
    0.91
    lets
    0.83
     lets
    0.75
     Lett
    0.75
    Lets
    0.74
    Act Density 0.425%

    No Known Activations