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

    Neuronpedia

    INDEX
    Explanations

    phrases related to heat or warmth

    oai_token-act-pair · gpt-3.5-turbo

    references to heat and temperature

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Goff
    -0.75
    lus
    -0.73
     Mandela
    -0.71
    uthor
    -0.66
    ufact
    -0.66
     Lynd
    -0.66
    ournal
    -0.65
     Commando
    -0.64
    VICE
    -0.63
    ledged
    -0.63
    POSITIVE LOGITS
    hens
    1.38
    wave
    1.30
    waves
    1.22
    seekers
    1.19
    stroke
    1.12
     exch
    1.09
    hen
    0.98
     exhaustion
    0.94
    seeking
    0.93
     waves
    0.93
    Act Density 0.050%

    No Known Activations