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

    Neuronpedia

    INDEX
    Explanations

    words related to tragic events, such as injuries, fatalities, and legal actions

    oai_token-act-pair · gpt-3.5-turbo

    situations involving harm, victims, and the implications of violence or legal issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     caut
    -0.70
     blat
    -0.68
    apest
    -0.65
     enqu
    -0.61
    icult
    -0.55
     advoc
    -0.54
     compan
    -0.54
    Firstly
    -0.53
     ner
    -0.53
     REPL
    -0.52
    POSITIVE LOGITS
     during
    0.91
     amid
    0.79
     onstage
    0.77
    thood
    0.74
    during
    0.74
     stemming
    0.73
     pursuant
    0.73
     after
    0.73
     afterward
    0.72
     when
    0.72
    Act Density 0.775%

    No Known Activations