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

    Neuronpedia

    INDEX
    Explanations

    quotations and various punctuation marks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Unnamed
    -0.15
    _('
    -0.15
    koli
    -0.13
    arse
    -0.13
    omite
    -0.13
     perpetual
    -0.13
    gnore
    -0.13
    945
    -0.13
    elez
    -0.13
    zte
    -0.13
    POSITIVE LOGITS
    itzer
    0.16
    alaria
    0.15
    indle
    0.15
    odable
    0.14
     Roose
    0.14
     Blanch
    0.14
    crow
    0.14
    uten
    0.13
     reinst
    0.13
    ekyll
    0.13
    Act Density 0.079%

    No Known Activations