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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating emotional states or feelings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.27
    1:0.09
    2:0.04
    3:0.03
    4:0.03
    5:0.15
    6:0.02
    7:0.05
    8:0.14
    9:0.04
    10:0.03
    11:0.05
    Negative Logits
    inals
    -2.13
    anz
    -1.88
    inate
    -1.84
    mouth
    -1.74
    abase
    -1.73
    chet
    -1.69
    eworks
    -1.68
    ayson
    -1.68
     rounds
    -1.66
    ―
    -1.65
    POSITIVE LOGITS
     opting
    2.35
     installing
    2.30
     fostering
    2.28
     restoring
    2.20
     selecting
    2.19
     choosing
    2.14
     importing
    2.12
     navigating
    2.10
     introducing
    2.09
     pract
    2.09
    Act Density 0.032%

    No Known Activations