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

    Neuronpedia

    INDEX
    Explanations

    compound names or titles, particularly those that are two-part and likely of German origin

    oai_token-act-pair · gpt-4-turbo

    the word "Brom" or the term "Bromley"

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly related to locations and brands

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    natureconservancy
    -0.74
    REAM
    -0.64
    ENC
    -0.64
    CEPT
    -0.63
    prise
    -0.62
    IDENT
    -0.62
     McCain
    -0.61
    selection
    -0.60
     LCS
    -0.59
     Lisbon
    -0.59
    POSITIVE LOGITS
    wich
    1.24
     Brom
    0.91
    aic
    0.91
    thal
    0.87
    cil
    0.82
    sten
    0.81
    ibl
    0.80
    spr
    0.79
    inatory
    0.78
    hal
    0.75
    Act Density 0.010%

    No Known Activations