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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "said" and its variations in reported speech

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    StructEnd
    -0.59
     itſelf
    -0.57
    UrlResolution
    -0.57
    HideFlags
    -0.56
     Numerade
    -0.56
     oprot
    -0.56
     BoxFit
    -0.56
     AssemblyCulture
    -0.55
     ModelRenderer
    -0.54
    thinkable
    -0.54
    POSITIVE LOGITS
     referring
    0.96
     adding
    0.76
     referencing
    0.75
     refiri
    0.71
     Referring
    0.66
    Referring
    0.65
     explaining
    0.63
     noting
    0.60
     quoting
    0.58
     regarding
    0.57
    Act Density 0.090%

    No Known Activations