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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate specific durations or time references in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.01
    2:0.13
    3:0.05
    4:0.08
    5:0.02
    6:0.13
    7:0.34
    8:0.02
    9:0.02
    10:0.04
    11:0.08
    Negative Logits
     cleaners
    -1.59
    witch
    -1.56
     assorted
    -1.49
    uggle
    -1.47
    abled
    -1.46
    avering
    -1.42
    athetic
    -1.39
    irlfriend
    -1.34
     srfAttach
    -1.34
    mbuds
    -1.33
    POSITIVE LOGITS
    uberty
    1.41
     proceedings
    1.38
    imester
    1.36
     ceremony
    1.33
    NAS
    1.30
     brackets
    1.30
     AST
    1.28
     ceremonies
    1.26
    iov
    1.25
     Voy
    1.25
    Act Density 0.010%

    No Known Activations