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

    Neuronpedia

    INDEX
    Explanations

    phrases related to discrepancies or variations in product representation

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

    Differences or variations

    np_acts-logits-general · gemini-2.0-flash

    slight differences or may differ

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     defaultstate
    -0.63
     CreateTagHelper
    -0.53
    __':
    -0.49
    ContentAlignment
    -0.49
    ülle
    -0.48
    strates
    -0.46
    ってきました
    -0.46
    idopsis
    -0.46
    SOUNDBITE
    -0.45
     curse
    -0.44
    POSITIVE LOGITS
     vary
    0.87
     varies
    0.85
     sometimes
    0.81
     ممکن
    0.78
     may
    0.77
    sometimes
    0.75
    不一定
    0.74
     varying
    0.73
     Varies
    0.72
     differ
    0.72
    Act Density 0.448%

    No Known Activations