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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate the beginning or early stages of events or seasons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ĶåĽŀ
    -0.15
     pump
    -0.15
    elif
    -0.15
    nal
    -0.14
    ergus
    -0.14
    awei
    -0.14
    .scalablytyped
    -0.14
    ãĥ¬ãĥĥãĥĪ
    -0.14
    ẹp
    -0.14
    itet
    -0.14
    POSITIVE LOGITS
    erras
    0.18
    ENTRY
    0.15
     hasher
    0.15
    vas
    0.15
    VERT
    0.15
     Wikip
    0.15
    venir
    0.14
     Observer
    0.14
    Offsets
    0.14
     Singer
    0.14
    Act Density 0.015%

    No Known Activations