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

    Neuronpedia

    INDEX
    Explanations

    programming language functions and their definitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    illian
    -0.16
    unan
    -0.15
    cue
    -0.14
     Obr
    -0.14
    ystone
    -0.13
    ean
    -0.13
    obra
    -0.13
    eyse
    -0.13
    alc
    -0.13
    ichen
    -0.13
    POSITIVE LOGITS
    (self
    0.46
     self
    0.44
    self
    0.34
    	self
    0.33
    -self
    0.32
    =self
    0.31
    [self
    0.30
    :self
    0.29
    *self
    0.28
     Self
    0.28
    Act Density 0.005%

    No Known Activations