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

    Neuronpedia

    INDEX
    Explanations

    references to intrinsic properties or values

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    tvguidetime
    -0.95
    tvr
    -0.90
    pausal
    -0.88
    Datuak
    -0.87
    !*\
    -0.86
    NgModule
    -0.84
    互联网档案馆
    -0.84
     $*$
    -0.83
    djangoproject
    -0.78
     Bevan
    -0.78
    POSITIVE LOGITS
     Sz
    0.98
     Hig
    0.84
    Sz
    0.81
    insic
    0.75
    Hig
    0.74
     wsz
    0.72
     uns
    0.70
     vig
    0.70
    Intrinsic
    0.69
     Szcz
    0.66
    Act Density 0.028%

    No Known Activations