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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating resistance or opposition to authority or established systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.04
    1:0.02
    2:0.14
    3:0.05
    4:0.32
    5:0.03
    6:0.02
    7:0.02
    8:0.13
    9:0.11
    10:0.04
    11:0.02
    Negative Logits
    ussen
    -1.67
    NAS
    -1.65
    ndra
    -1.61
    phabet
    -1.50
    ��
    -1.48
     largeDownload
    -1.47
    emouth
    -1.47
    umption
    -1.43
    rawdownloadcloneembedreportprint
    -1.43
    owe
    -1.42
    POSITIVE LOGITS
     resistance
    1.61
    TEXTURE
    1.59
    ドラ
    1.55
     resists
    1.48
     phosphate
    1.39
     barriers
    1.37
     SCP
    1.30
     repe
    1.30
     magnesium
    1.29
     resistant
    1.27
    Act Density 0.005%

    No Known Activations