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

    Neuronpedia

    INDEX
    Explanations

    mentions of receiving or collecting funds

    oai_token-act-pair · gpt-3.5-turbo

    references to source or origin, particularly financial contributions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mask
    -0.81
    aqu
    -0.80
    olit
    -0.78
    otype
    -0.76
    motion
    -0.75
    faced
    -0.75
    clear
    -0.74
    position
    -0.74
    ographic
    -0.73
    Flash
    -0.73
    POSITIVE LOGITS
     afar
    1.15
     abroad
    1.11
     whence
    0.99
     thence
    0.92
     Dominion
    0.78
     scratch
    0.78
     anywhere
    0.78
     taxation
    0.77
     overseas
    0.75
     royalties
    0.75
    Act Density 0.135%

    No Known Activations