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

    Neuronpedia

    INDEX
    Explanations

    pronouns and references to people or entities in conversations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.03
    2:0.13
    3:0.20
    4:0.02
    5:0.05
    6:0.05
    7:0.08
    8:0.13
    9:0.09
    10:0.08
    11:0.08
    Negative Logits
    ORPG
    -1.34
    aez
    -1.16
     sqor
    -1.16
    arily
    -1.11
    clerosis
    -1.08
    orically
    -1.07
    emort
    -1.05
    itionally
    -1.03
    ificantly
    -1.02
     Siren
    -1.02
    POSITIVE LOGITS
     walls
    1.06
     bends
    1.05
     confines
    1.02
     bushes
    0.98
     scenes
    0.97
     junction
    0.97
     Lines
    0.95
    Dispatch
    0.95
     horns
    0.94
     ropes
    0.94
    Act Density 0.013%

    No Known Activations