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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing personal beliefs or opinions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.03
    1:0.02
    2:0.07
    3:0.12
    4:0.09
    5:0.06
    6:0.07
    7:0.05
    8:0.08
    9:0.12
    10:0.13
    11:0.09
    Negative Logits
     Alleg
    -1.26
     Independence
    -1.25
     Kad
    -1.18
     polyg
    -1.18
     Sparks
    -1.13
     Gener
    -1.12
     Fusion
    -1.12
     Princ
    -1.12
     KR
    -1.10
     Apache
    -1.10
    POSITIVE LOGITS
    BuyableInstoreAndOnline
    1.63
    };
    1.61
    endif
    1.56
     };
    1.44
    orage
    1.41
    cember
    1.38
    icter
    1.38
    })
    1.36
    },
    1.35
    kees
    1.34
    Act Density 0.049%

    No Known Activations