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

    Neuronpedia

    INDEX
    Explanations

    dashes and hyphens in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ertiary
    -0.18
    umber
    -0.15
    ubo
    -0.15
    addon
    -0.14
    olls
    -0.14
    âĢŀM
    -0.14
    ebb
    -0.14
    âĢŀP
    -0.14
     باع
    -0.14
    yms
    -0.13
    POSITIVE LOGITS
     and
    0.27
     hence
    0.25
     or
    0.25
     something
    0.21
     but
    0.20
     which
    0.20
     a
    0.20
     it
    0.20
     including
    0.20
     -
    0.19
    Act Density 0.125%

    No Known Activations