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

    Neuronpedia

    INDEX
    Explanations

    expressions of personal opinions and judgments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ertino
    -0.16
     Click
    -0.15
     click
    -0.14
    avour
    -0.14
     Despite
    -0.14
     CLICK
    -0.14
    ataka
    -0.14
    .this
    -0.13
    -this
    -0.13
    Ïģκ
    -0.13
    POSITIVE LOGITS
    Plus
    0.25
     Plus
    0.25
     plus
    0.24
    plus
    0.24
     PLUS
    0.23
    .plus
    0.20
    ETA
    0.20
     EDIT
    0.19
    EDIT
    0.19
    PLUS
    0.18
    Act Density 0.475%

    No Known Activations