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

    Neuronpedia

    INDEX
    Explanations

    references to different forms of harassment, including verbal, sexual, and street harassment

    oai_token-act-pair · gpt-3.5-turbo

    references to harassment, particularly in a social or political context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    éĹĺ
    -0.95
    stanbul
    -0.82
    zyme
    -0.81
    ACTED
    -0.78
    ECD
    -0.71
    inet
    -0.71
    ortium
    -0.71
    rient
    -0.71
    olesterol
    -0.70
    ether
    -0.70
    POSITIVE LOGITS
     harassment
    0.96
     harass
    0.95
     harassing
    0.90
     tactics
    0.86
     accus
    0.82
     harassed
    0.79
     stalking
    0.79
    assment
    0.78
     leveled
    0.73
     complaints
    0.73
    Act Density 0.037%

    No Known Activations