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

    Neuronpedia

    INDEX
    Explanations

    expressions related to requests for input or responses from the audience

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.07
    1:0.08
    2:0.07
    3:0.08
    4:0.09
    5:0.08
    6:0.09
    7:0.08
    8:0.07
    9:0.08
    10:0.09
    11:0.07
    Negative Logits
     Elliott
    -2.58
     Lawrence
    -2.52
     Allison
    -2.42
    charged
    -2.42
     Parks
    -2.41
     Horn
    -2.38
     Halls
    -2.37
     Wiley
    -2.34
    Howard
    -2.33
    Rich
    -2.32
    POSITIVE LOGITS
    BIP
    2.90
    =$
    2.78
     "$:/
    2.78
     Anarch
    2.70
    itsu
    2.67
     captcha
    2.59
    jug
    2.57
     Syri
    2.51
    VPN
    2.48
    vier
    2.48
    Act Density 0.000%

    No Known Activations