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

    Neuronpedia

    INDEX
    Explanations

    phrases related to negative events or problems that have impacted certain entities or regions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to negative impacts or consequences affecting communities or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aunder
    -0.77
    ascript
    -0.71
    ighters
    -0.70
    aler
    -0.66
    augh
    -0.65
    olf
    -0.65
    ãĥ¼ãĥ³
    -0.65
     sidx
    -0.64
     consulted
    -0.64
    OTE
    -0.63
    POSITIVE LOGITS
     havoc
    0.98
     us
    0.86
     him
    0.84
     humankind
    0.79
     them
    0.76
     everyone
    0.76
     everybody
    0.75
     humanity
    0.75
    edIn
    0.74
     Jaw
    0.73
    Act Density 0.168%

    No Known Activations