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

    Neuronpedia

    INDEX
    Explanations

    phrases that involve comparisons or similarities

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

    similes and comparisons using "as if" constructions.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Negative Logits
    NUMX
    -0.49
    liferay
    -0.49
     Cyprus
    -0.45
    phrine
    -0.45
     Hamas
    -0.44
    boutin
    -0.43
    ftagPool
    -0.43
     CRS
    -0.43
     GMP
    -0.42
    loit
    -0.42
    POSITIVE LOGITS
     будто
    1.39
     seolah
    1.27
     словно
    1.14
     jakby
    1.12
     like
    1.01
     כא
    0.90
    仿佛
    0.89
     như
    0.87
     as
    0.86
    まるで
    0.86
    Act Density 0.195%

    No Known Activations