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

    Neuronpedia

    INDEX
    Explanations

    terms related to various forms of abuse, such as physical, emotional, or financial abuse

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "abuse" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cil
    -0.79
    izen
    -0.77
    travel
    -0.76
     Hurricanes
    -0.70
    eday
    -0.70
    ebus
    -0.69
    pard
    -0.69
    puter
    -0.66
     adventurer
    -0.65
    mand
    -0.65
    POSITIVE LOGITS
    abuse
    0.94
     abuse
    0.90
     abusing
    0.89
     abused
    0.84
     abuses
    0.80
     Abuse
    0.78
     tactics
    0.76
     inflicted
    0.75
     perpetrated
    0.75
    fully
    0.73
    Act Density 0.021%

    No Known Activations