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

    Neuronpedia

    INDEX
    Explanations

    references to bridging gaps or inequalities in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ðħ
    -0.15
    MLE
    -0.15
     ambigu
    -0.15
    otts
    -0.14
    ogie
    -0.14
    argas
    -0.14
    qs
    -0.14
    sdk
    -0.14
    .Invalid
    -0.14
     bast
    -0.13
    POSITIVE LOGITS
     gap
    0.80
    gap
    0.69
     Gap
    0.69
    Gap
    0.65
    -gap
    0.60
     gaps
    0.58
    _gap
    0.58
     GAP
    0.49
    _GAP
    0.45
     divide
    0.36
    Act Density 0.166%

    No Known Activations