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

    Neuronpedia

    INDEX
    Explanations

    percentages and expressions of accuracy in decision-making contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sbin
    -0.15
     generations
    -0.15
    mie
    -0.14
    hic
    -0.14
    inde
    -0.13
    åīįçļĦ
    -0.13
    ye
    -0.13
    activ
    -0.13
    aversable
    -0.13
     strang
    -0.13
    POSITIVE LOGITS
     occasions
    0.42
     times
    0.37
     instances
    0.31
     occasion
    0.30
    times
    0.29
     veces
    0.27
     vezes
    0.26
    instances
    0.26
    æŶåĢĻ
    0.26
     ocas
    0.25
    Act Density 0.083%

    No Known Activations