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

    Neuronpedia

    INDEX
    Explanations

    phrases that express contrast or opposition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ancia
    -0.07
    .must
    -0.07
    zos
    -0.07
     sice
    -0.07
     ë¿IJ
    -0.07
    bak
    -0.07
    UGE
    -0.07
    NotNull
    -0.06
     ikke
    -0.06
    uang
    -0.06
    POSITIVE LOGITS
     actual
    0.11
     actually
    0.09
    actual
    0.08
     proper
    0.08
     Actually
    0.08
     Actual
    0.08
    Actually
    0.08
    羣æŃ£
    0.07
     real
    0.07
    (actual
    0.07
    Act Density 0.039%

    No Known Activations