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

    Neuronpedia

    INDEX
    Explanations

    expressions of desire or reluctance to engage in activities or confrontations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    IGO
    -0.17
    atch
    -0.15
    avo
    -0.14
    tein
    -0.14
    scribed
    -0.14
     verg
    -0.14
    roman
    -0.14
    ÙħاÙĨÛĮ
    -0.14
    urbation
    -0.14
    igo
    -0.14
    POSITIVE LOGITS
     anymore
    0.22
    γκο
    0.17
    ÑĦи
    0.16
    Aceptar
    0.16
     Lose
    0.16
    loses
    0.15
    orte
    0.15
     nor
    0.15
    ëŀ
    0.15
    ä»»ä½ķ
    0.15
    Act Density 0.066%

    No Known Activations