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

    Neuronpedia

    INDEX
    Explanations

    terms related to mathematical definitions and structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ölkerung
    -0.55
    intellij
    -0.55
     instead
    -0.53
    instead
    -0.50
     utafiti
    -0.49
    vertissement
    -0.49
     Sanz
    -0.48
    west
    -0.47
    springframework
    -0.47
     invece
    -0.46
    POSITIVE LOGITS
     always
    0.93
    always
    0.93
     Always
    0.90
    Always
    0.88
     alltid
    0.85
     ALWAYS
    0.83
    ALWAYS
    0.83
     תמיד
    0.81
     zawsze
    0.79
     Siempre
    0.78
    Act Density 2.537%

    No Known Activations