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

    Neuronpedia

    INDEX
    Explanations

    clauses indicating future actions or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.01
    2:0.14
    3:0.06
    4:0.10
    5:0.03
    6:0.05
    7:0.11
    8:0.05
    9:0.05
    10:0.22
    11:0.10
    Negative Logits
     PSU
    -1.68
     Logic
    -1.55
     Mathematics
    -1.55
     Argon
    -1.49
     decimal
    -1.45
     MBA
    -1.45
     honorary
    -1.44
     Statistical
    -1.42
     footnote
    -1.38
     awarded
    -1.37
    POSITIVE LOGITS
    覚醒
    1.55
    abiding
    1.52
     unsus
    1.51
    umbn
    1.51
    rises
    1.50
     advoc
    1.50
    ressive
    1.50
    tnc
    1.50
    rha
    1.49
    �
    1.49
    Act Density 0.001%

    No Known Activations