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

    Neuronpedia

    INDEX
    Explanations

    references to specific names and terms associated with scientific theories and contributions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    providedIn
    -0.82
    atm
    -0.70
    yam
    -0.69
     abbin
    -0.68
     }^{[
    -0.68
    alen
    -0.67
     Bowden
    -0.67
     Moser
    -0.66
    izr
    -0.66
    eqn
    -0.65
    POSITIVE LOGITS
     himſelf
    0.86
     Antioch
    0.86
    arschijnlijk
    0.85
    quierda
    0.85
     Arend
    0.85
     myſelf
    0.85
     Võ
    0.83
     Efq
    0.83
    BagConstraints
    0.82
     Soledad
    0.81
    Act Density 2.068%

    No Known Activations