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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "Paradise" or variations of it

    oai_token-act-pair · gpt-3.5-turbo

    the presence of the word "Par" or its variations within a context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    BOOK
    -0.79
    ONSORED
    -0.75
     deed
    -0.74
    士
    -0.68
    sie
    -0.68
    galitarian
    -0.68
     breeze
    -0.66
    éĹĺ
    -0.66
    mens
    -0.65
     fixme
    -0.65
    POSITIVE LOGITS
    liament
    1.23
    allel
    1.09
     ILCS
    0.94
    hesda
    0.92
     pall
    0.77
    querade
    0.77
    gomery
    0.76
    Par
    0.74
    lehem
    0.74
    acent
    0.74
    Act Density 0.008%

    No Known Activations