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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal matters or arrests

    oai_token-act-pair · gpt-3.5-turbo

    the presence of specific conversational prompts or statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aii
    -0.97
    otics
    -0.79
    alion
    -0.79
    illus
    -0.79
    ĪĴ
    -0.79
    aza
    -0.76
    VW
    -0.72
    ichael
    -0.72
    ains
    -0.72
    aleigh
    -0.72
    POSITIVE LOGITS
    Publisher
    0.68
     println
    0.61
    reach
    0.61
     msec
    0.61
    bodied
    0.59
    serving
    0.59
     Psychiat
    0.59
    diagn
    0.59
    adj
    0.58
     Publisher
    0.57
    Act Density 0.000%

    No Known Activations