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

    Neuronpedia

    INDEX
    Explanations

    references to the word "the" and its variations in phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     decidedly
    -0.77
     admittedly
    -0.72
    WithMany
    -0.57
     ostensibly
    -0.56
    presumably
    -0.53
     fraught
    -0.52
     étr
    -0.52
     nécessairement
    -0.51
    Somewhat
    -0.51
     désormais
    -0.51
    POSITIVE LOGITS
    mergeFrom
    0.79
    ChildScrollView
    0.77
     equipments
    0.76
     said
    0.74
     ſtate
    0.74
     purpoſe
    0.73
    },[])
    0.72
    — 
    0.72
    styleType
    0.71
     feedbacks
    0.71
    Act Density 0.872%

    No Known Activations