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

    Neuronpedia

    INDEX
    Explanations

    expressions related to conditionality and expectation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    GRE
    -0.15
    INTR
    -0.15
    å®ĩ
    -0.14
    tar
    -0.14
    _ud
    -0.14
    rief
    -0.14
    ighton
    -0.14
    ilter
    -0.14
    lád
    -0.14
    emit
    -0.14
    POSITIVE LOGITS
    ardy
    0.18
    721
    0.15
     Marketable
    0.15
     lo
    0.15
    256
    0.15
     Kir
    0.14
    berman
    0.14
     Starr
    0.14
    oks
    0.14
    SYM
    0.14
    Act Density 0.031%

    No Known Activations