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

    Neuronpedia

    INDEX
    Explanations

    conditional phrases and exceptions in narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ustral
    -0.17
    raith
    -0.16
    rieg
    -0.14
    âĶģâĶģâĶģâĶģâĶģâĶģâĶģâĶģâĶģâĶģâĶģâĶģâĶģâĶģâĶģâĶģ
    -0.14
    irc
    -0.14
    Occurred
    -0.13
    βε
    -0.13
    phalt
    -0.13
    lem
    -0.13
    AIT
    -0.13
    POSITIVE LOGITS
     apart
    0.20
     aside
    0.18
    azen
    0.16
    ebek
    0.16
     пÑĢоÑĩ
    0.15
     Apart
    0.14
     besides
    0.14
    istes
    0.14
     mö
    0.14
    aside
    0.14
    Act Density 0.033%

    No Known Activations