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

    Neuronpedia

    INDEX
    Explanations

    proper names of individuals

    oai_token-act-pair · gpt-3.5-turbo

    names and references associated with specific individuals and companies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ecake
    -0.69
    Lenin
    -0.68
    ablishment
    -0.68
    eers
    -0.68
    perate
    -0.65
     Dragonbound
    -0.63
    eering
    -0.63
    orney
    -0.63
    upt
    -0.62
    edience
    -0.60
    POSITIVE LOGITS
    aird
    0.83
    halla
    0.81
    oil
    0.75
    INGTON
    0.74
    iffs
    0.71
    fish
    0.70
    flies
    0.65
    otor
    0.65
    OTH
    0.64
     Lanc
    0.64
    Act Density 0.026%

    No Known Activations