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

    Neuronpedia

    INDEX
    Explanations

    sequences or patterns featuring hyphens

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Reviewed
    -0.71
    speak
    -0.70
    Tex
    -0.65
    gettable
    -0.64
    iere
    -0.63
    Accessory
    -0.62
    someone
    -0.62
    Attributes
    -0.62
     Journals
    -0.61
    resist
    -0.61
    POSITIVE LOGITS
     Sanford
    0.67
    isks
    0.65
    omas
    0.64
     Ocean
    0.63
     Warner
    0.63
     RAND
    0.62
    ulia
    0.62
    oshenko
    0.61
     Major
    0.61
    anz
    0.59
    Act Density 0.011%

    No Known Activations