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

    Neuronpedia

    INDEX
    Explanations

    instances of significant actions or attributes related to approval and assessment in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Desk
    -0.17
     Rob
    -0.16
     Desk
    -0.15
    edm
    -0.15
    edback
    -0.15
    rug
    -0.15
     Robbins
    -0.15
    rob
    -0.14
    bole
    -0.14
    vais
    -0.14
    POSITIVE LOGITS
    206
    0.15
    ìł¸
    0.14
    atus
    0.14
     ============================================================================↵
    0.14
     Sizes
    0.14
    inka
    0.14
    aux
    0.14
    igr
    0.14
    erase
    0.13
    iline
    0.13
    Act Density 0.022%

    No Known Activations