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

    Neuronpedia

    INDEX
    Explanations

    terms related to destruction or accidents, particularly involving physical objects like ships or buildings

    oai_token-act-pair · gpt-3.5-turbo

    the word "wreck" and its variations, indicative of destruction or disaster

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cius
    -0.77
    ulton
    -0.69
    arettes
    -0.67
    raviolet
    -0.66
    istrates
    -0.65
     Flavoring
    -0.65
    romy
    -0.63
    OSH
    -0.63
     Kov
    -0.60
     Lich
    -0.60
    POSITIVE LOGITS
     havoc
    1.47
    wreck
    1.02
     wre
    1.02
     wreck
    0.97
    dump
    0.85
    driver
    0.84
    load
    0.80
    cks
    0.75
    yard
    0.72
     Dive
    0.71
    Act Density 0.029%

    No Known Activations