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

    Neuronpedia

    INDEX
    Explanations

    phrases related to criminal activities, particularly assault and harassment

    oai_token-act-pair · gpt-3.5-turbo

    references to acts of violence or assault

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    spection
    -0.79
    gio
    -0.72
    emption
    -0.72
    HCR
    -0.71
    join
    -0.71
    venants
    -0.70
    ahime
    -0.69
    ItemImage
    -0.69
    bet
    -0.69
    ventures
    -0.69
    POSITIVE LOGITS
     unsuspecting
    1.18
     entire
    1.03
     offending
    0.98
     hardest
    0.91
     innocent
    0.89
     weakest
    0.88
     targets
    0.88
     opponent
    0.87
     nearest
    0.87
     target
    0.87
    Act Density 0.322%

    No Known Activations