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

    Neuronpedia

    INDEX
    Explanations

    phrases that refer to a large quantity or numerous examples

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    esis
    -0.16
    ược
    -0.14
    lore
    -0.14
    semb
    -0.14
     nutshell
    -0.14
     soon
    -0.14
    htags
    -0.13
    _ASSUME
    -0.13
    ARGIN
    -0.13
    htag
    -0.13
    POSITIVE LOGITS
    ways
    0.20
     ways
    0.19
    strstr
    0.15
    owitz
    0.15
    erdale
    0.15
    .vars
    0.14
     Ways
    0.14
    kla
    0.14
    iae
    0.14
    inke
    0.13
    Act Density 0.097%

    No Known Activations