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

    Neuronpedia

    INDEX
    Explanations

    conditional phrases indicating potential actions or outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ised
    -0.17
    sted
    -0.17
    izedName
    -0.16
    .scalablytyped
    -0.15
    arius
    -0.15
    contres
    -0.15
    arel
    -0.15
    yr
    -0.15
    ized
    -0.14
    .bunifuFlatButton
    -0.14
    POSITIVE LOGITS
    nt
    0.35
    NT
    0.22
     potentially
    0.22
     be
    0.21
     conce
    0.20
     possibly
    0.20
    've
    0.19
    ’ve
    0.19
    ÂŃn
    0.18
    /w
    0.17
    Act Density 0.087%

    No Known Activations