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

    Neuronpedia

    INDEX
    Explanations

    conjunctions and transitions in statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.07
    1:0.09
    2:0.07
    3:0.08
    4:0.09
    5:0.07
    6:0.09
    7:0.07
    8:0.08
    9:0.08
    10:0.07
    11:0.07
    Negative Logits
     moth
    -2.35
     extortion
    -2.33
    thora
    -2.28
    roo
    -2.19
     demolition
    -2.10
     Leilan
    -1.99
     eternity
    -1.98
     ell
    -1.98
    flation
    -1.96
     pulp
    -1.93
    POSITIVE LOGITS
    PH
    2.31
    APH
    2.18
     PH
    2.16
     Peer
    1.98
    outheast
    1.94
     elig
    1.92
    BU
    1.90
     Leban
    1.89
    irt
    1.89
    displayText
    1.88
    Act Density 0.000%

    No Known Activations