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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and inequalities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ANGE
    -0.17
    esar
    -0.15
    å·
    -0.15
    gae
    -0.14
     prob
    -0.14
    å£
    -0.13
    Sizer
    -0.13
    jej
    -0.13
    å
    -0.13
    tel
    -0.13
    POSITIVE LOGITS
    uvw
    0.22
    81
    0.21
    16
    0.20
    729
    0.19
    ab
    0.19
     ab
    0.19
    625
    0.19
    27
    0.18
    64
    0.18
     abc
    0.18
    Act Density 0.100%

    No Known Activations