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

    Neuronpedia

    INDEX
    Explanations

    references to authority or official statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     sentier
    -0.43
     fija
    -0.39
    CascadeType
    -0.39
     veux
    -0.38
     Verpflich
    -0.36
     acompañado
    -0.36
     Exactos
    -0.35
     conveyed
    -0.35
     państw
    -0.35
     Sotto
    -0.35
    POSITIVE LOGITS
     about
    0.56
    :✨
    0.52
    PYX
    0.51
     propOrder
    0.50
    ZX
    0.48
    ulemon
    0.48
    antMatchers
    0.48
    RTLD
    0.44
    soort
    0.44
    ErrUnexpectedEOF
    0.44
    Act Density 0.501%

    No Known Activations