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

    Neuronpedia

    INDEX
    Explanations

    proper nouns or names

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns or names, particularly those starting with specific letters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    terday
    -0.96
    theless
    -0.81
     compe
    -0.75
     parity
    -0.74
     sanity
    -0.72
     wise
    -0.72
    etheless
    -0.70
     unison
    -0.67
    é¾įå¥ij士
    -0.66
     profiling
    -0.66
    POSITIVE LOGITS
    onian
    1.06
    ospels
    0.94
    venth
    0.89
    seys
    0.88
    leys
    0.88
    intern
    0.86
    ocene
    0.83
     Hotel
    0.83
    osphere
    0.82
    isphere
    0.82
    Act Density 0.340%

    No Known Activations