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

    Neuronpedia

    INDEX
    Explanations

    terms related to assaults and weapons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    stral
    -0.15
    argout
    -0.15
     Challenger
    -0.14
    ÑģÑĮко
    -0.14
    //{{
    -0.14
    oser
    -0.13
     Kling
    -0.13
     Roths
    -0.13
    trs
    -0.13
    .au
    -0.13
    POSITIVE LOGITS
    ive
    0.19
    amon
    0.18
    amerate
    0.17
    able
    0.16
    al
    0.16
    iveness
    0.15
     Scalia
    0.15
    anton
    0.15
    گاÙĩ
    0.14
    ardi
    0.14
    Act Density 0.012%

    No Known Activations