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

    Neuronpedia

    INDEX
    Explanations

    phrases or terms related to conditions and their implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    coming
    -0.19
    sik
    -0.17
    thing
    -0.16
    ache
    -0.16
    ležit
    -0.15
    аÑİ
    -0.15
    ediator
    -0.15
    aso
    -0.14
    æ¡Ī
    -0.14
    ме
    -0.14
    POSITIVE LOGITS
    ally
    0.32
    ality
    0.32
    nement
    0.30
    als
    0.27
    nal
    0.24
     precedent
    0.22
    naires
    0.20
    naire
    0.20
     ripe
    0.19
    izr
    0.17
    Act Density 0.036%

    No Known Activations