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

    Neuronpedia

    INDEX
    Explanations

    references to a particular individual named Sal

    oai_token-act-pair · gpt-3.5-turbo

    the word "Sal" and its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     depreciation
    -0.72
    STEP
    -0.71
    lihood
    -0.69
     Compton
    -0.64
    ãģĨ
    -0.62
     timelines
    -0.62
     halftime
    -0.61
     Dominion
    -0.60
    å¸
    -0.60
     periphery
    -0.59
    POSITIVE LOGITS
    isbury
    1.51
    omon
    1.45
    mone
    1.35
    azar
    1.31
    utations
    1.30
    adin
    1.16
    ient
    1.14
    utation
    1.14
    vation
    1.13
    erno
    1.13
    Act Density 0.019%

    No Known Activations