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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating emphasis or comparison

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing absoluteness or specificity in statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     towed
    -0.68
     Registry
    -0.64
    veyard
    -0.63
     crowned
    -0.62
     Ashe
    -0.62
     blaze
    -0.62
     Shell
    -0.62
     sidelined
    -0.62
     Register
    -0.61
     cylinder
    -0.61
    POSITIVE LOGITS
    optim
    0.85
    negative
    0.82
    positive
    0.77
    some
    0.77
    FU
    0.76
    angers
    0.73
    anger
    0.73
    blank
    0.73
    significant
    0.72
    oths
    0.70
    Act Density 0.314%

    No Known Activations