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

    Neuronpedia

    INDEX
    Explanations

    pronouns followed by auxiliary verbs

    oai_token-act-pair · gpt-3.5-turbo

    expressions of uncertainty or speculation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    interstitial
    -0.83
    å¾
    -0.72
    worldly
    -0.68
     è£ıç
    -0.65
    ä¸Ĭ
    -0.65
     Mehran
    -0.63
    SpaceEngineers
    -0.62
    Initialized
    -0.62
    ãĤ»
    -0.61
    SPONSORED
    -0.61
    POSITIVE LOGITS
     certainly
    1.20
     however
    1.19
     furthermore
    1.11
     moreover
    1.09
     also
    1.05
     definitely
    0.98
     therefore
    0.90
     dunno
    0.89
    Still
    0.89
     ALSO
    0.87
    Act Density 0.809%

    No Known Activations