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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating inquiry and belief, particularly in relation to personal experiences or perspectives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Personendaten
    -0.72
     somewhere
    -0.60
    PullParser
    -0.59
    somewhere
    -0.57
     Everywhere
    -0.56
     Todos
    -0.56
     Somewhere
    -0.53
    Everywhere
    -0.53
    LEncoder
    -0.52
    everywhere
    -0.52
    POSITIVE LOGITS
     anything
    2.94
    anything
    2.34
     Anything
    2.23
    Anything
    2.14
     ANYTHING
    1.84
     nothing
    1.52
     nothin
    1.42
     aught
    1.35
     nada
    1.27
     nimic
    1.25
    Act Density 0.269%

    No Known Activations