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

    Neuronpedia

    INDEX
    Explanations

    conditional phrases indicating hypothetical situations or outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vais
    -0.14
     Jew
    -0.14
    HideInInspector
    -0.14
    üre
    -0.14
    ungi
    -0.14
     Bern
    -0.13
    ommen
    -0.13
    ogn
    -0.13
     Davidson
    -0.13
     Briggs
    -0.13
    POSITIVE LOGITS
     analogue
    0.15
    itsu
    0.15
    üc
    0.14
     Bender
    0.14
     çķ
    0.14
    umb
    0.13
    atchet
    0.13
     münchen
    0.13
     èĩ
    0.13
     tức
    0.13
    Act Density 0.965%

    No Known Activations