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

    Neuronpedia

    INDEX
    Explanations

    phrases related to changes or the concept of altering a situation

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to change and assistance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    multiple
    -0.67
    alian
    -0.63
    ortment
    -0.61
    abouts
    -0.60
    itled
    -0.59
    eg
    -0.59
    lique
    -0.58
    ãĥ¼ãĥ³
    -0.58
    rogens
    -0.58
    auri
    -0.58
    POSITIVE LOGITS
     anything
    1.26
     anybody
    1.20
     anymore
    1.19
     nor
    1.19
     anyone
    1.06
     whatsoever
    1.03
     either
    0.97
    nor
    0.94
     slightest
    0.94
     any
    0.94
    Act Density 0.237%

    No Known Activations