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

    Neuronpedia

    INDEX
    Explanations

    terms related to feedback and changes in state or condition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    よいよ
    -0.40
    dafx
    -0.37
    buya
    -0.36
    ParallelGroup
    -0.36
     Talmud
    -0.35
    evos
    -0.35
     suspens
    -0.34
     Padang
    -0.33
     Berlín
    -0.33
    )++;
    -0.33
    POSITIVE LOGITS
    MessageTagHelper
    0.60
     regresar
    0.59
     afterwards
    0.59
     обратно
    0.57
     afterward
    0.54
     regreso
    0.54
     nakalista
    0.53
     retorno
    0.52
     retour
    0.52
     ritorno
    0.50
    Act Density 0.694%

    No Known Activations