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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the exclusion or negation of possibilities in a scientific context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    ruling out possibilities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     laikā
    -0.47
    ETHING
    -0.47
    boneca
    -0.43
     pantaloni
    -0.43
     navideño
    -0.42
     riemp
    -0.42
    niña
    -0.42
     navideña
    -0.42
     lentement
    -0.42
    ismet
    -0.41
    POSITIVE LOGITS
     possibility
    0.71
     descart
    0.60
     rejection
    0.57
     possibilities
    0.57
    reject
    0.57
     chances
    0.56
     reject
    0.56
    possibility
    0.55
     rejecting
    0.55
     Possibility
    0.54
    Act Density 0.025%

    No Known Activations