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

    Neuronpedia

    INDEX
    Explanations

    instances of uncertainty or doubt expressed in thoughts or feelings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ſelf
    -0.72
     purpoſe
    -0.72
     eſt
    -0.67
     Valentín
    -0.64
    GHIJKLM
    -0.63
     ſch
    -0.62
     enfans
    -0.61
     auffi
    -0.61
    ">+
    -0.60
     Chriftian
    -0.60
    POSITIVE LOGITS
    Somehow
    1.49
     Somehow
    1.39
     somehow
    1.37
     magically
    0.91
     strangely
    0.91
    Somewhere
    0.80
     irgendwie
    0.80
     oddly
    0.79
     weirdly
    0.77
     mysteriously
    0.76
    Act Density 0.129%

    No Known Activations