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

    Neuronpedia

    INDEX
    Explanations

    gerunds and related suffixes in various contexts

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     iſt
    -1.16
     Anſ
    -1.16
     ſche
    -1.14
     myſelf
    -1.13
     ſta
    -1.12
     raiſ
    -1.09
     anſ
    -1.08
     beſ
    -1.06
     ſind
    -1.06
     Jefus
    -1.06
    POSITIVE LOGITS
    -
    0.71
     المعيارى
    0.58
     or
    0.57
     getClient
    0.55
     and
    0.54
    
    0.54
    eneral
    0.53
     termos
    0.52
    \}\\
    0.52
    netes
    0.51
    Act Density 0.961%

    No Known Activations