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

    Neuronpedia

    INDEX
    Explanations

    phrases related to being in prison or behind bars

    oai_token-act-pair · gpt-3.5-turbo

    references to incarceration or imprisonment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ctive
    -1.05
    ULAR
    -0.80
    aneous
    -0.78
    actus
    -0.72
    ulously
    -0.72
    ples
    -0.71
     GENERAL
    -0.70
    itional
    -0.69
    RECT
    -0.69
    vier
    -0.68
    POSITIVE LOGITS
    manship
    0.93
    hips
    0.89
    cape
    0.87
    hift
    0.85
     bars
    0.84
    eters
    0.82
    poons
    0.80
    mith
    0.78
    hirt
    0.78
    poon
    0.76
    Act Density 0.034%

    No Known Activations