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

    Neuronpedia

    INDEX
    Explanations

    mentions of individuals holding prominent or authoritative positions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "lead" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Mach
    -0.68
    apy
    -0.64
    terday
    -0.64
    phis
    -0.63
    ategor
    -0.63
    ongyang
    -0.62
    afort
    -0.62
    orrow
    -0.61
     sunset
    -0.61
    ITT
    -0.61
    POSITIVE LOGITS
    lead
    0.92
    better
    0.87
    boards
    0.84
     Leading
    0.77
    pipe
    0.73
    ership
    0.70
    ãĥĥãĥī
    0.70
     lead
    0.69
     leading
    0.68
     Lead
    0.68
    Act Density 0.026%

    No Known Activations