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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "appeal" and its variations, indicating a focus on desires and requests

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ed
    -0.17
    ya
    -0.16
    ega
    -0.14
    ngth
    -0.14
    chai
    -0.14
    es
    -0.14
     seedu
    -0.14
    lu
    -0.13
    ollen
    -0.13
    /people
    -0.13
    POSITIVE LOGITS
     minded
    0.18
    -minded
    0.16
    435
    0.15
    ptide
    0.15
     appeals
    0.15
    oppins
    0.15
     lanc
    0.14
    夫人
    0.14
    inceton
    0.14
    alach
    0.14
    Act Density 0.026%

    No Known Activations