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

    Neuronpedia

    INDEX
    Explanations

    words related to conflicts or confrontations between individuals or groups

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    liest
    -0.69
    lest
    -0.66
    riad
    -0.65
    ym
    -0.63
    odor
    -0.63
    osc
    -0.63
    atus
    -0.62
    aca
    -0.61
    otin
    -0.61
    cus
    -0.61
    POSITIVE LOGITS
     alike
    1.63
     respectively
    1.46
     depending
    0.98
    depending
    0.94
     amongst
    0.69
     throughout
    0.69
    SPONSORED
    0.68
    atever
    0.66
     simultaneously
    0.65
     characterize
    0.63
    Act Density 0.414%

    No Known Activations