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

    Neuronpedia

    INDEX
    Explanations

    references to clothing items and their characteristics

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

    warmth or insulation

    np_acts-logits-general · gemini-2.0-flash

    warmth and feeling cozy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     cref
    -0.59
     June
    -0.58
     watermelon
    -0.57
    JULY
    -0.57
     bluzka
    -0.56
    June
    -0.55
     July
    -0.54
     Watermelon
    -0.54
     lysis
    -0.53
     Juin
    -0.53
    POSITIVE LOGITS
     warmth
    1.35
     warm
    1.32
     Warm
    1.26
    Warm
    1.18
     warmest
    1.17
     warming
    1.17
     warms
    1.13
    warm
    1.13
     WARM
    1.12
     warmer
    1.09
    Act Density 0.142%

    No Known Activations