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

    Neuronpedia

    INDEX
    Explanations

    words related to links or connections

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "inks" or variations of it

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     foundation
    -0.69
    560
    -0.65
     contend
    -0.65
     Sharif
    -0.63
    brance
    -0.62
    ש
    -0.60
    ALLY
    -0.59
     basis
    -0.58
     Lancet
    -0.58
    Bron
    -0.57
    POSITIVE LOGITS
    inks
    1.32
    omething
    0.99
    redients
    0.96
    hots
    0.94
    hops
    0.93
    terness
    0.91
    ertodd
    0.89
    inking
    0.87
    iewicz
    0.84
    orno
    0.84
    Act Density 0.009%

    No Known Activations