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

    Neuronpedia

    INDEX
    Explanations

    numerical values and data comparing experimental results

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ProtoMessage
    -0.49
    archiviato
    -0.46
    findpost
    -0.44
    delwed
    -0.43
    TagMode
    -0.42
     compañ
    -0.42
     Taw
    -0.40
    jewództ
    -0.40
     يتيمه
    -0.38
     ujednoznacz
    -0.38
    POSITIVE LOGITS
    TagHelpers
    0.51
    Demografie
    0.38
     Delay
    0.38
     delay
    0.38
    ggar
    0.37
    IConfiguration
    0.37
    fromCharCode
    0.37
    brug
    0.36
     Gun
    0.36
    延
    0.36
    Act Density 0.893%

    No Known Activations