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

    Neuronpedia

    INDEX
    Explanations

    words related to capes and escape

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

    cape, scape, scope, sphere

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ônibus
    -0.39
     armée
    -0.39
     caminhão
    -0.38
    testens
    -0.38
     imageNamed
    -0.38
     écrivain
    -0.37
     במש
    -0.36
     hom
    -0.35
    MLLoader
    -0.35
     Infórmanos
    -0.34
    POSITIVE LOGITS
    cape
    3.00
    capes
    2.27
    scape
    2.19
    Scape
    2.17
    SCAPE
    2.14
    CAPE
    1.73
     scape
    1.68
     cape
    1.63
    caping
    1.60
    caped
    1.48
    Act Density 0.005%

    No Known Activations