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

    Neuronpedia

    INDEX
    Explanations

    contractions and informal language indicative of dialogue

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.09
    1:0.28
    2:0.04
    3:0.03
    4:0.03
    5:0.22
    6:0.03
    7:0.03
    8:0.06
    9:0.05
    10:0.05
    11:0.04
    Negative Logits
    �
    -1.86
     Parables
    -1.78
    dra
    -1.78
    û
    -1.77
    iery
    -1.73
    OPA
    -1.73
    dor
    -1.71
    º
    -1.71
    ERA
    -1.70
    idium
    -1.69
    POSITIVE LOGITS
     work
    2.01
     worked
    1.83
     working
    1.82
     Work
    1.77
     works
    1.65
     worker
    1.65
    work
    1.63
     WORK
    1.62
     cook
    1.58
     revel
    1.57
    Act Density 0.008%

    No Known Activations