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

    Neuronpedia

    INDEX
    Explanations

    special characters and formatting symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    AsUp
    -0.83
    djangoproject
    -0.82
     AssemblyCulture
    -0.73
     po
    -0.71
    SequentialGroup
    -0.71
    RepeatedField
    -0.70
    [toxicity=0]
    -0.66
    uxxxx
    -0.65
    ()]
    -0.61
    nocache
    -0.61
    POSITIVE LOGITS
     pleaſure
    1.09
    !("{
    1.08
     raiſ
    1.04
     juſt
    1.00
     ſen
    0.97
     Anſ
    0.97
    ="@+
    0.96
     Inſ
    0.95
     purpoſe
    0.92
     faſt
    0.92
    Act Density 0.113%

    No Known Activations