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

    Neuronpedia

    INDEX
    Explanations

    affirmative statements or expressions related to existence or presence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    efault
    -0.15
     savory
    -0.14
    ãģĩ
    -0.14
    esktop
    -0.13
    undy
    -0.13
    stricted
    -0.13
    inions
    -0.13
     Hil
    -0.13
    ÄįÃŃ
    -0.13
    tryside
    -0.13
    POSITIVE LOGITS
    abel
    0.15
     fet
    0.15
    abelle
    0.15
     {}.
    0.14
    isy
    0.14
    zia
    0.14
    leton
    0.14
    icio
    0.13
     altern
    0.13
     action
    0.13
    Act Density 0.678%

    No Known Activations