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

    Neuronpedia

    INDEX
    Explanations

    words related to intention or meaning

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "mean to."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    zyme
    -0.69
    Myth
    -0.69
     fa
    -0.67
    sbm
    -0.65
     Sabha
    -0.63
     pse
    -0.63
     Hemp
    -0.62
     netted
    -0.61
    govtrack
    -0.60
     bandwagon
    -0.58
    POSITIVE LOGITS
    thood
    0.92
    uni
    0.77
    neutral
    0.68
    full
    0.66
    ortium
    0.66
    ëĭ
    0.65
    arenthood
    0.65
     fullest
    0.64
    pelling
    0.63
    ints
    0.63
    Act Density 0.080%

    No Known Activations