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

    Neuronpedia

    INDEX
    Explanations

    phrases related to making arrangements or providing instructions

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

    Text snippets preceding non-English words

    np_acts-logits-general · gemini-2.0-flash

    static, MRI, installation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Personensuche
    -0.85
     Roskov
    -0.82
     pleaſure
    -0.67
    AnchorStyles
    -0.65
     judiciales
    -0.65
    ImageContext
    -0.64
     ſche
    -0.64
     resourceCulture
    -0.63
     apă
    -0.63
     stället
    -0.60
    POSITIVE LOGITS
     entire
    0.88
     same
    0.88
     latter
    0.76
     biggest
    0.73
    entire
    0.72
     main
    0.68
     ENTIRE
    0.67
     story
    0.67
    biggest
    0.67
     largest
    0.67
    Act Density 0.026%

    No Known Activations