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

    Neuronpedia

    INDEX
    Explanations

    references to the color pink or associated terms in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.05
    1:0.03
    2:0.25
    3:0.10
    4:0.15
    5:0.05
    6:0.02
    7:0.02
    8:0.06
    9:0.14
    10:0.05
    11:0.02
    Negative Logits
    ��
    -1.81
    BIL
    -1.48
    ngth
    -1.43
    gregation
    -1.37
    者
    -1.36
    izational
    -1.33
    =-=-=-=-
    -1.32
    utenberg
    -1.31
    ertation
    -1.29
     conclud
    -1.28
    POSITIVE LOGITS
    stro
    1.40
     cheeks
    1.21
    paper
    1.19
    ilings
    1.18
    ioxide
    1.16
     olive
    1.15
    reme
    1.13
    rish
    1.12
     cigarettes
    1.10
    pires
    1.10
    Act Density 0.004%

    No Known Activations