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

    Neuronpedia

    INDEX
    Explanations

    phrases related to time and transitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     autorytatywna
    -0.74
     defaultstate
    -0.74
    Tembelea
    -0.70
     ModelExpression
    -0.69
     Efq
    -0.68
    ftagPool
    -0.63
    MigrationBuilder
    -0.62
    Personensuche
    -0.61
     Houſe
    -0.61
    Rhestr
    -0.60
    POSITIVE LOGITS
     also
    0.42
     This
    0.41
     furthermore
    0.40
     lo
    0.40
     therefore
    0.38
     Do
    0.37
     Thus
    0.36
     Mehr
    0.36
     Furthermore
    0.35
     doesn
    0.35
    Act Density 1.229%

    No Known Activations