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

    Neuronpedia

    INDEX
    Explanations

    alternative ways to present options or suggestions

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

    Preceding alternatives or options

    np_acts-logits-general · gemini-2.0-flash

    suggesting an alternative

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Majefty
    -0.85
     ―――――
    -0.83
     Shakspeare
    -0.76
     OnInit
    -0.73
     MonoBehaviour
    -0.73
    WebElementEntity
    -0.72
     greateſt
    -0.71
     Theſe
    -0.71
    ⋙
    -0.71
    AndEndTag
    -0.70
    POSITIVE LOGITS
     alternatively
    1.02
     simply
    0.93
     else
    0.81
    simply
    0.79
     if
    0.76
     just
    0.72
    Else
    0.70
     же
    0.69
     equivalently
    0.69
     alternately
    0.68
    Act Density 0.189%

    No Known Activations