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

    Neuronpedia

    INDEX
    Explanations

    names, most likely related to people

    oai_token-act-pair · gpt-3.5-turbo

    sequences of letters that commonly appear in names or proper nouns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĤ¼ãĤ¦ãĤ¹
    -0.70
    Spread
    -0.69
     loophole
    -0.62
    SPONSORED
    -0.61
     contradictions
    -0.59
     conveniently
    -0.58
     charism
    -0.58
     envy
    -0.57
     matched
    -0.56
     needle
    -0.55
    POSITIVE LOGITS
    kefeller
    0.95
    issance
    0.86
    restling
    0.79
    zl
    0.78
    ophone
    0.73
    backer
    0.72
    ighters
    0.71
    iger
    0.70
    earchers
    0.70
    undo
    0.69
    Act Density 0.098%

    No Known Activations