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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating uncertainty or incongruity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ✨:
    -0.59
     XNUMX
    -0.58
    AutoScaleMode
    -0.58
     Flin
    -0.56
     acido
    -0.56
     "..\..\..\
    -0.55
    krivelse
    -0.55
     repatriation
    -0.54
     generazione
    -0.54
    Còn
    -0.52
    POSITIVE LOGITS
     somehow
    1.49
    Somewhere
    1.44
    Somehow
    1.43
     Somehow
    1.36
     Somewhere
    1.34
     somewhere
    1.34
    somewhere
    1.31
    Somebody
    1.26
     something
    1.15
     Something
    1.14
    Act Density 0.242%

    No Known Activations