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

    Neuronpedia

    INDEX
    Explanations

    phrases related to sharing experiences or resources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    931
    -0.20
    ukan
    -0.15
    stup
    -0.15
     ########.
    -0.15
    uft
    -0.15
     vrai
    -0.14
    teness
    -0.14
    umper
    -0.14
    FRING
    -0.14
    uber
    -0.14
    POSITIVE LOGITS
     share
    0.75
    share
    0.60
     Share
    0.54
     SHARE
    0.53
    -share
    0.51
    Share
    0.51
     fair
    0.50
    .share
    0.47
    _share
    0.46
     shares
    0.41
    Act Density 0.046%

    No Known Activations