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

    Neuronpedia

    INDEX
    Explanations

    important keywords or phrases that indicate time and relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ampus
    -0.18
    ilst
    -0.17
    ugo
    -0.15
    chin
    -0.14
     Gilbert
    -0.14
    мÑĥ
    -0.14
    Scaled
    -0.14
    á»Ļn
    -0.13
    άλ
    -0.13
    berry
    -0.13
    POSITIVE LOGITS
    inka
    0.17
     caret
    0.16
    bject
    0.15
    idget
    0.14
    964
    0.14
    amel
    0.14
     formally
    0.13
    ipop
    0.13
     ORIGINAL
    0.13
     moments
    0.13
    Act Density 0.003%

    No Known Activations