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

    Neuronpedia

    INDEX
    Explanations

    variations of the verb "say" and expressions of speech

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     <<<<<<<<<<<<<<
    -0.72
    ']")
    -0.69
     Staub
    -0.66
     Malte
    -0.65
    ChildScrollView
    -0.63
    teness
    -0.61
     useRouter
    -0.61
    tagHelperRunner
    -0.60
    TagHelpers
    -0.58
    Dez
    -0.57
    POSITIVE LOGITS
     SAY
    1.03
     Say
    1.01
     goodbye
    0.95
    SAY
    0.92
    Say
    0.91
     Says
    0.85
    say
    0.85
     say
    0.83
     says
    0.82
     SAYS
    0.81
    Act Density 0.100%

    No Known Activations