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

    Neuronpedia

    INDEX
    Explanations

    references to boxing techniques and training practices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ardu
    -0.17
    oric
    -0.16
    asha
    -0.15
     Bowl
    -0.15
    istrovstvÃŃ
    -0.14
    ryn
    -0.14
    ipple
    -0.14
    ibold
    -0.14
    zzle
    -0.14
    hte
    -0.14
    POSITIVE LOGITS
    onica
    0.17
    enet
    0.16
     GarcÃŃa
    0.16
    ochen
    0.15
    empo
    0.15
    umba
    0.14
    onaut
    0.14
    onian
    0.13
     tempo
    0.13
     nominees
    0.13
    Act Density 0.009%

    No Known Activations