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

    Neuronpedia

    INDEX
    Explanations

    information about positive developments or occurrences

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "good news."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    senal
    -0.84
    sf
    -0.74
    urat
    -0.70
    ĸļ
    -0.68
    ngth
    -0.67
    ONSORED
    -0.67
    ancies
    -0.65
    amation
    -0.64
     sweat
    -0.64
     sediment
    -0.63
    POSITIVE LOGITS
    peak
    0.76
    night
    0.71
     Roundup
    0.71
     Tonight
    0.69
    Catholic
    0.68
    rief
    0.66
    stadt
    0.66
     regarding
    0.66
    mith
    0.66
    ayers
    0.65
    Act Density 0.045%

    No Known Activations