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

    Neuronpedia

    INDEX
    Explanations

    definitions or formal constructs in a technical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    #+#
    -0.54
    tées
    -0.46
     exclusively
    -0.46
     μο
    -0.46
     typically
    -0.46
     nahilalakip
    -0.46
     Kolon
    -0.45
     Aal
    -0.45
     arguably
    -0.44
     potret
    -0.44
    POSITIVE LOGITS
     define
    1.76
    define
    1.70
     Define
    1.63
    Define
    1.58
     definition
    1.49
    definition
    1.41
     defines
    1.34
     Definition
    1.34
     defin
    1.28
     definitions
    1.28
    Act Density 0.260%

    No Known Activations