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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating uncertainty or conditionality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Follows "Whether" (or similar word)

    np_acts-logits-general · gemini-2.0-flash

    whether... or

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    EDEFAULT
    -0.91
     HttpNotFound
    -0.84
     beginnetje
    -0.83
     BnF
    -0.81
     saites
    -0.79
    SceneManagement
    -0.77
     Infórmanos
    -0.77
     milf
    -0.77
    expandindo
    -0.76
     ModelRenderer
    -0.76
    POSITIVE LOGITS
     they
    1.18
     there
    1.11
     it
    1.08
     we
    0.90
     he
    0.83
     this
    0.80
     you
    0.74
     she
    0.72
     indeed
    0.66
    there
    0.66
    Act Density 0.080%

    No Known Activations