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

    Neuronpedia

    INDEX
    Explanations

    terms related to evaluating performance

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to performance or effectiveness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    :\
    -0.76
    ubs
    -0.76
    ãĤ´ãĥ³
    -0.75
    ãĥĩãĤ£
    -0.74
    ATOR
    -0.73
    Sov
    -0.71
    pez
    -0.70
    ERO
    -0.69
    eni
    -0.69
    iewicz
    -0.69
    POSITIVE LOGITS
     invested
    0.73
     they
    0.70
     compiled
    0.70
     fired
    0.70
    idious
    0.70
     pursu
    0.67
     militar
    0.67
     propelled
    0.67
     elapsed
    0.67
     awaited
    0.66
    Act Density 0.039%

    No Known Activations