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

    Neuronpedia

    INDEX
    Explanations

    words related to fire and emergency services

    oai_token-act-pair · gpt-3.5-turbo

    references to fire or related emergency services

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ortium
    -0.74
    士
    -0.72
    urat
    -0.70
    matically
    -0.69
    sonian
    -0.68
    rome
    -0.67
    ually
    -0.64
    lez
    -0.63
    nostic
    -0.63
    sylv
    -0.62
    POSITIVE LOGITS
    ĪĴ
    0.81
     destro
    0.75
     extingu
    0.71
     Brigade
    0.70
     Shotgun
    0.69
     fury
    0.66
     brim
    0.65
     espresso
    0.63
     Charg
    0.63
     Rockets
    0.60
    Act Density 0.276%

    No Known Activations