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

    Neuronpedia

    INDEX
    Explanations

    phrases related to crime and criminal activities

    oai_token-act-pair · gpt-3.5-turbo

    terms related to crime and criminal activity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lihood
    -0.81
    hof
    -0.73
     Oo
    -0.69
    FORM
    -0.68
     Centauri
    -0.67
    VALUE
    -0.66
     VIDEOS
    -0.66
    zl
    -0.64
    lists
    -0.63
    \\\\\\\\
    -0.63
    POSITIVE LOGITS
    inals
    1.00
    crim
    0.95
    inally
    0.93
    psy
    0.87
    eware
    0.86
    pter
    0.84
    ilant
    0.84
    orig
    0.80
    acies
    0.80
     Crim
    0.79
    Act Density 0.018%

    No Known Activations