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

    Neuronpedia

    INDEX
    Explanations

    words related to shrinking

    oai_token-act-pair · gpt-3.5-turbo

    references to shrines and related structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Prospect
    -0.77
    eering
    -0.66
     Gutenberg
    -0.65
    insula
    -0.64
    lace
    -0.63
    gradient
    -0.61
     Trojan
    -0.61
    POL
    -0.61
     Hebdo
    -0.60
    DVD
    -0.60
    POSITIVE LOGITS
     shr
    1.21
    abies
    0.91
    ivas
    0.89
    aii
    0.82
    ines
    0.82
    Ń·
    0.79
    astically
    0.79
    inks
    0.76
     gardens
    0.76
    bush
    0.76
    Act Density 0.005%

    No Known Activations