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

    Neuronpedia

    INDEX
    Explanations

    comparisons or contrasts between different concepts or entities

    oai_token-act-pair · gpt-3.5-turbo

    comparisons and contrasts between opposing concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oker
    -0.73
    iband
    -0.70
    cffffcc
    -0.69
    eri
    -0.67
    istar
    -0.65
    atern
    -0.65
    aspers
    -0.64
    aston
    -0.64
    akening
    -0.63
    ortal
    -0.63
    POSITIVE LOGITS
     hers
    0.84
     theirs
    0.81
     nurture
    0.77
     ours
    0.72
     damned
    0.65
     equals
    0.64
     adversity
    0.64
     reality
    0.63
    gew
    0.62
     dr
    0.62
    Act Density 0.196%

    No Known Activations