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

    Neuronpedia

    INDEX
    Explanations

    comparative and superlative adjectives or expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    699
    -0.14
    rei
    -0.14
     cups
    -0.14
    amera
    -0.14
    52
    -0.13
    red
    -0.13
    55
    -0.13
    _ping
    -0.13
     reg
    -0.13
     guilty
    -0.13
    POSITIVE LOGITS
     instead
    0.20
    instead
    0.19
    ihan
    0.17
    Instead
    0.16
     вмеÑģÑĤ
    0.16
    PELL
    0.16
    士
    0.15
     Instead
    0.15
     !***
    0.15
    awe
    0.15
    Act Density 0.187%

    No Known Activations