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

    Neuronpedia

    INDEX
    Explanations

    discussions around purpose, connection, and the human experience

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     tölt
    -0.56
     Stolz
    -0.54
     Independencia
    -0.54
     ejus
    -0.53
     anello
    -0.53
     emplois
    -0.50
     inconvénients
    -0.49
     reluctance
    -0.49
     Vertrauen
    -0.49
     Seaman
    -0.49
    POSITIVE LOGITS
    LookAnd
    0.85
     الحره
    0.80
    WriteTagHelper
    0.75
    openzeppelin
    0.74
    IVEREF
    0.72
    ArgsConstructor
    0.72
    NOPQRST
    0.71
     CreateTagHelper
    0.68
     humanity
    0.67
     human
    0.66
    Act Density 0.094%

    No Known Activations