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

    Neuronpedia

    INDEX
    Explanations

    modal verbs indicating potential or necessity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Seym
    -0.76
     Vaugh
    -0.71
     Olymp
    -0.61
     marqu
    -0.58
     advoc
    -0.55
     pursu
    -0.55
    Math
    -0.52
     pursuit
    -0.52
     Afgh
    -0.52
    —-
    -0.51
    POSITIVE LOGITS
    Ĥª
    0.75
    obyl
    0.68
    urtles
    0.65
    metics
    0.64
     hereby
    0.64
    rael
    0.62
     guiActiveUnfocused
    0.60
    )?
    0.60
    tics
    0.60
    zbollah
    0.59
    Act Density 0.257%

    No Known Activations