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

    Neuronpedia

    INDEX
    Explanations

    context-specific variables that influence outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    migrationBuilder
    -0.54
     pull
    -0.52
    äch
    -0.51
     Pull
    -0.50
     فريبيس
    -0.49
     betweenstory
    -0.49
     distanciation
    -0.49
    ticons
    -0.49
    oneofs
    -0.49
    |}{$
    -0.49
    POSITIVE LOGITS
     depends
    1.11
     Depends
    1.07
    depends
    1.06
     depending
    1.03
     tergantung
    0.94
     afhankelijk
    0.94
    depending
    0.93
     dependant
    0.92
     dependent
    0.91
     dipende
    0.89
    Act Density 0.091%

    No Known Activations