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

    Neuronpedia

    INDEX
    Explanations

    proper nouns or names followed by some associated actions or events

    oai_token-act-pair · gpt-3.5-turbo

    phrases or terms related to personal identity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ichick
    -0.70
    tons
    -0.70
    backer
    -0.69
    thouse
    -0.69
    omic
    -0.67
    tery
    -0.65
    kson
    -0.64
    roller
    -0.64
    leigh
    -0.64
    pay
    -0.63
    POSITIVE LOGITS
     CITY
    1.44
    ANA
    1.29
    VILLE
    1.29
    ARA
    1.20
     COUNTY
    1.20
    ING
    1.16
    ANE
    1.14
    LET
    1.14
    AN
    1.13
    ANG
    1.12
    Act Density 0.071%

    No Known Activations