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

    Neuronpedia

    INDEX
    Explanations

    expressions of uncertainty or second-guessing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pom
    -0.20
    ________________
    -0.20
    umb
    -0.17
    edm
    -0.17
    âĶģâĶģ
    -0.17
    ############
    -0.17
    buch
    -0.17
    onomy
    -0.16
    p
    -0.16
    ipping
    -0.16
    POSITIVE LOGITS
    ming
    0.32
    atically
    0.27
    med
    0.24
    orphic
    0.23
    ichael
    0.21
    nesty
    0.21
    my
    0.21
    olecular
    0.21
    ERICAN
    0.20
    ixture
    0.20
    Act Density 1.147%

    No Known Activations