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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating agreement or affirmation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ########.
    -0.58
    IVEREF
    -0.57
    SharedDtor
    -0.57
    #+#
    -0.57
    CrossRef
    -0.56
    VideoCapture
    -0.54
    PMailer
    -0.51
     AssemblyProduct
    -0.50
     ProtoMessage
    -0.50
    GEBURTSDATUM
    -0.49
    POSITIVE LOGITS
    arakhand
    0.69
    tamol
    0.69
     AspNetCore
    0.68
     unſ
    0.63
    erdings
    0.62
     zufolge
    0.62
     zároveň
    0.61
     beware
    0.60
     AUSSI
    0.59
     ladri
    0.59
    Act Density 0.175%

    No Known Activations