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

    Neuronpedia

    INDEX
    Explanations

    terms related to advantages and benefits in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ish
    -0.18
    variants
    -0.16
    ling
    -0.15
    ãĥ«ãĤ¯
    -0.15
    linger
    -0.15
    reh
    -0.14
    sky
    -0.14
    rott
    -0.14
    ÑĩаÑĤ
    -0.14
    ÄĽÅ¾
    -0.13
    POSITIVE LOGITS
    ously
    0.38
    ous
    0.31
    /dis
    0.28
    ably
    0.27
    OUS
    0.24
    antages
    0.21
    antly
    0.20
    MENTS
    0.19
     over
    0.17
    ait
    0.16
    Act Density 0.019%

    No Known Activations