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

    Neuronpedia

    INDEX
    Explanations

    words relating to advice or guidance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ivant
    -0.17
    iate
    -0.14
    paced
    -0.14
     Accord
    -0.14
    ween
    -0.14
    issen
    -0.14
    zon
    -0.14
     Sym
    -0.14
    ê²°
    -0.14
     Immediate
    -0.14
    POSITIVE LOGITS
    ster
    0.27
    sters
    0.27
    -tip
    0.24
    pling
    0.23
    per
    0.23
    .tip
    0.23
    pler
    0.23
     Tip
    0.22
    ple
    0.22
     tip
    0.21
    Act Density 0.013%

    No Known Activations