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

    Neuronpedia

    INDEX
    Explanations

    characters or symbols that are used in technical contexts, particularly related to programming or mathematical notation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.04
    1:0.04
    2:0.11
    3:0.05
    4:0.03
    5:0.04
    6:0.05
    7:0.06
    8:0.03
    9:0.04
    10:0.37
    11:0.10
    Negative Logits
     Hicks
    -2.51
     Hayden
    -2.42
     Tanaka
    -2.33
     fringe
    -1.98
     Short
    -1.98
     shortstop
    -1.94
     Hass
    -1.93
     Brist
    -1.92
     clearance
    -1.91
     ABE
    -1.90
    POSITIVE LOGITS
    �
    4.31
    ��
    3.13
    ł
    3.10
    ��
    2.80
    �
    2.59
    lot
    2.49
    ov
    2.38
    ogens
    2.32
    jong
    2.31
    oshop
    2.30
    Act Density 0.000%

    No Known Activations