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

    Neuronpedia

    INDEX
    Explanations

    numbers indicating probability or likelihood

    oai_token-act-pair · gpt-3.5-turbo

    references to odds or probabilities in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Materials
    -0.83
    tein
    -0.74
    artney
    -0.74
    afort
    -0.74
    resent
    -0.72
    ufact
    -0.71
    uala
    -0.71
    Contents
    -0.71
    TPP
    -0.70
     Imaging
    -0.69
    POSITIVE LOGITS
     odds
    1.09
    lash
    0.79
    manship
    0.78
     ratio
    0.73
     worsh
    0.72
     against
    0.72
     peg
    0.70
     collide
    0.70
    heet
    0.69
     Whedon
    0.69
    Act Density 0.015%

    No Known Activations