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

    Neuronpedia

    INDEX
    Explanations

    numerical dates and references to specific occurrences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.09
    1:0.02
    2:0.03
    3:0.07
    4:0.03
    5:0.06
    6:0.01
    7:0.43
    8:0.09
    9:0.02
    10:0.06
    11:0.04
    Negative Logits
    uria
    -2.57
     Gerry
    -2.52
     typew
    -2.52
     destro
    -2.51
     cler
    -2.51
    stadt
    -2.42
     typ
    -2.40
     canv
    -2.31
    oslov
    -2.31
     substitute
    -2.25
    POSITIVE LOGITS
    Gaza
    2.74
    �
    2.63
    Iran
    2.50
    panic
    2.46
    CRE
    2.35
    ISIS
    2.29
    �
    2.23
    https
    2.20
    Hillary
    2.20
    Marco
    2.19
    Act Density 0.008%

    No Known Activations