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

    Neuronpedia

    INDEX
    Explanations

    phrases related to positive qualities or actions

    oai_token-act-pair · gpt-3.5-turbo

    favorable assessments or recommendations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atars
    -0.81
    noxious
    -0.71
    Downloadha
    -0.68
    pora
    -0.63
    ĸļ
    -0.63
    tf
    -0.62
    igham
    -0.60
    doms
    -0.59
    verified
    -0.58
    otom
    -0.58
    POSITIVE LOGITS
     outweigh
    0.85
    ounters
    0.78
    smanship
    0.72
     answ
    0.70
     (>
    0.67
    nered
    0.64
    ãĤ®
    0.64
    ipeg
    0.63
     outwe
    0.60
    Angelo
    0.59
    Act Density 0.413%

    No Known Activations