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

    Neuronpedia

    INDEX
    Explanations

    phrases related to evaluations and judgments concerning suitability and eligibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    podob
    -0.16
     slož
    -0.15
    enia
    -0.15
    onica
    -0.15
    <=(
    -0.15
    STALL
    -0.15
    /loose
    -0.14
    CallCheck
    -0.14
    _tA
    -0.14
    uhan
    -0.14
    POSITIVE LOGITS
     excluded
    0.76
     exclusion
    0.75
     exclude
    0.71
     excludes
    0.62
    exclude
    0.62
    Exclude
    0.60
     Exclude
    0.59
    .exclude
    0.58
     exclus
    0.55
     excluding
    0.55
    Act Density 0.397%

    No Known Activations