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

    Neuronpedia

    INDEX
    Explanations

    words related to explosives and detonation

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with explosives and detonations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SEA
    -0.74
    İ
    -0.74
    Reviewer
    -0.71
    esan
    -0.69
    tyard
    -0.68
    ħĭ
    -0.68
     Parables
    -0.67
    leg
    -0.66
    chal
    -0.65
    anson
    -0.65
    POSITIVE LOGITS
     detonated
    1.19
     deton
    1.12
     combust
    0.91
    uating
    0.88
     bombs
    0.85
     explosives
    0.84
    alore
    0.82
     rall
    0.82
     grenades
    0.82
     prematurely
    0.81
    Act Density 0.034%

    No Known Activations