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

    Neuronpedia

    INDEX
    Explanations

    instances of value judgments and evaluations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atak
    -0.17
    .appspot
    -0.15
    alace
    -0.15
     eiusmod
    -0.15
    .Undef
    -0.14
    bellion
    -0.14
     Damn
    -0.14
    uez
    -0.14
    htar
    -0.14
    .study
    -0.14
    POSITIVE LOGITS
     option
    0.22
     added
    0.22
     following
    0.22
     possibility
    0.20
     prospect
    0.20
     distinct
    0.18
     suggestion
    0.18
     ability
    0.17
     novel
    0.16
     proposition
    0.16
    Act Density 0.159%

    No Known Activations