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

    Neuronpedia

    INDEX
    Explanations

    words that introduce examples or instances

    oai_token-act-pair · gpt-3.5-turbo

    phrases that introduce examples or instances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ements
    -0.68
    alities
    -0.67
    orts
    -0.65
    atures
    -0.64
    lic
    -0.60
    orously
    -0.59
    fect
    -0.59
    forms
    -0.57
     unlaw
    -0.57
    Exit
    -0.57
    POSITIVE LOGITS
    ,,
    0.68
    mith
    0.65
    ðĿ
    0.63
    .,
    0.63
    ignt
    0.62
     owing
    0.62
    ,.
    0.60
     liking
    0.59
     âĸ
    0.58
    onto
    0.58
    Act Density 0.029%

    No Known Activations