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

    Neuronpedia

    INDEX
    Explanations

    phrases related to suggesting or expressing an opinion

    oai_token-act-pair · gpt-3.5-turbo

    phrases that include the word "say."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    RM
    -0.70
    obin
    -0.69
    Want
    -0.66
    mate
    -0.66
    hammad
    -0.65
    ason
    -0.62
    mar
    -0.60
    vin
    -0.60
    sf
    -0.59
    sv
    -0.59
    POSITIVE LOGITS
     diminishing
    0.67
    ilation
    0.66
    ucket
    0.64
    uyomi
    0.63
    idth
    0.62
     blasp
    0.60
    pmwiki
    0.60
    ivari
    0.60
    umbn
    0.60
    âĵĺ
    0.59
    Act Density 0.490%

    No Known Activations