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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating time or availability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yet
    -0.20
     yet
    -0.19
     crossings
    -0.16
    они
    -0.15
    heimer
    -0.14
     Lessons
    -0.13
     weakened
    -0.13
    lesh
    -0.13
    currently
    -0.13
     Likely
    -0.13
    POSITIVE LOGITS
     only
    0.23
     Only
    0.19
     ONLY
    0.19
    ONLY
    0.18
    åıªèĥ½
    0.17
    only
    0.17
    Only
    0.17
     ÑĤолÑĮко
    0.17
    aeda
    0.17
    tember
    0.16
    Act Density 0.051%

    No Known Activations