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

    Neuronpedia

    INDEX
    Explanations

    phrases related to existing or pre-existing conditions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to existing conditions or ongoing states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    izes
    -0.69
    alty
    -0.65
    izing
    -0.65
     Harbor
    -0.64
     ILCS
    -0.64
    isal
    -0.63
     noodles
    -0.62
     fisherman
    -0.60
    è¯
    -0.60
     mob
    -0.59
    POSITIVE LOGITS
    ipation
    0.84
    nesses
    0.82
    rodu
    0.79
    isting
    0.73
    alez
    0.71
    aid
    0.69
    aukee
    0.69
    nesday
    0.69
    existing
    0.68
    chwitz
    0.68
    Act Density 0.026%

    No Known Activations