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

    Neuronpedia

    INDEX
    Explanations

    references to victims in various contexts such as abuse, accidents, or legal cases

    oai_token-act-pair · gpt-3.5-turbo

    references to victims in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    CLASSIFIED
    -0.70
    OPLE
    -0.68
    GGGG
    -0.66
    ove
    -0.66
    REE
    -0.65
     Huck
    -0.63
    alter
    -0.63
    leaf
    -0.62
    yip
    -0.62
    Style
    -0.61
    POSITIVE LOGITS
     victims
    1.00
     Victims
    0.92
    vict
    0.90
     victim
    0.83
    izers
    0.82
     inflicted
    0.80
     Victim
    0.80
     Survivors
    0.77
    hip
    0.74
     succumbed
    0.74
    Act Density 0.021%

    No Known Activations