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

    Neuronpedia

    INDEX
    Explanations

    mentions of crime-related words or terms

    oai_token-act-pair · gpt-3.5-turbo

    words related to crime and criminal activity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lihood
    -0.84
     Centauri
    -0.82
    VIDEO
    -0.72
    FORM
    -0.71
    lists
    -0.69
    #$
    -0.68
    zl
    -0.66
     Annex
    -0.64
    hof
    -0.63
     Oo
    -0.62
    POSITIVE LOGITS
    inals
    1.00
    eware
    0.92
    inally
    0.89
    inatory
    0.88
    ming
    0.87
    etric
    0.86
    acies
    0.85
    inant
    0.82
    bers
    0.81
    orah
    0.81
    Act Density 0.029%

    No Known Activations