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

    Neuronpedia

    INDEX
    Explanations

    phrases that describe actions or sentiments characterized as significant or shocking

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    MarshalTo
    -0.55
    :+:
    -0.48
    WSGI
    -0.46
    IVersion
    -0.41
    بوابة
    -0.41
    InstanceState
    -0.41
     jsPsych
    -0.40
    pant
    -0.40
    obox
    -0.40
    spender
    -0.40
    POSITIVE LOGITS
     "..
    0.69
     "...
    0.64
     “…
    0.63
     “...
    0.63
    ]="
    0.61
     Describes
    0.60
     “(
    0.59
     “[
    0.59
    LEncoder
    0.59
     "[
    0.59
    Act Density 0.404%

    No Known Activations