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

    Neuronpedia

    INDEX
    Explanations

    expressions of laughter or amusement in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ivic
    -0.15
    unci
    -0.15
    icit
    -0.15
    ëĮĢë¡ľ
    -0.14
    amus
    -0.14
    omain
    -0.14
     Dod
    -0.14
    taj
    -0.13
    eparator
    -0.13
    ocale
    -0.13
    POSITIVE LOGITS
    aha
    0.29
    mph
    0.29
    ahaha
    0.27
    ah
    0.26
    mmm
    0.25
    m
    0.25
    oor
    0.24
    mm
    0.23
    ENCE
    0.23
    ence
    0.23
    Act Density 0.022%

    No Known Activations