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

    Neuronpedia

    INDEX
    Explanations

    expressions of appreciation and acknowledgment of support

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.03
    1:0.07
    2:0.05
    3:0.07
    4:0.30
    5:0.08
    6:0.05
    7:0.14
    8:0.03
    9:0.04
    10:0.03
    11:0.06
    Negative Logits
    ザ
    -2.57
     destro
    -2.47
    ModLoader
    -2.40
    CVE
    -2.33
    aughs
    -2.27
    EStream
    -2.23
     speculated
    -2.09
    olitan
    -2.05
     ])
    -2.05
    cedented
    -2.04
    POSITIVE LOGITS
    your
    6.55
    Your
    6.50
     your
    6.42
     yours
    6.29
     Your
    6.24
     yourself
    5.79
     you
    5.71
     yourselves
    5.68
     YOUR
    5.66
    you
    5.63
    Act Density 0.720%

    No Known Activations