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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "known" and its variations in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    incer
    -0.19
    ross
    -0.17
    angent
    -0.16
    ÄŁan
    -0.15
    dk
    -0.14
    ars
    -0.14
    istol
    -0.14
    ors
    -0.14
    leton
    -0.14
    ian
    -0.14
    POSITIVE LOGITS
     WithEvents
    0.18
    rops
    0.16
    spe
    0.15
    TRL
    0.14
    egal
    0.14
     TCHAR
    0.14
    wealth
    0.14
    ledge
    0.14
    QT
    0.14
    safe
    0.14
    Act Density 0.050%

    No Known Activations