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

    Neuronpedia

    INDEX
    Explanations

    expressions related to permission or enabling actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    YNC
    -0.82
     StatelessWidget
    -0.74
     než
    -0.71
     bains
    -0.70
     demais
    -0.69
    SessionFactory
    -0.68
     fatica
    -0.68
     démission
    -0.67
    »?
    -0.67
     cister
    -0.66
    POSITIVE LOGITS
     ALLOW
    1.56
    ALLOW
    1.52
     Allow
    1.47
     allow
    1.41
     allows
    1.40
     Allows
    1.39
     allowed
    1.37
    Allows
    1.32
    Allow
    1.31
     allowing
    1.30
    Act Density 0.121%

    No Known Activations