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

    Neuronpedia

    INDEX
    Explanations

    phrases that imply physical separation or removal from a particular context or location

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÐĴС
    -0.16
    bero
    -0.16
    Å¡il
    -0.16
    rif
    -0.15
    ickerView
    -0.15
    /Dk
    -0.15
    htub
    -0.14
    prefs
    -0.14
    ilage
    -0.14
    ìľł
    -0.14
    POSITIVE LOGITS
     behalf
    0.17
    esc
    0.16
    utsch
    0.15
    andre
    0.14
     duty
    0.14
     Craig
    0.14
    OLON
    0.13
    /off
    0.13
     reflection
    0.13
     неÑĹ
    0.13
    Act Density 0.032%

    No Known Activations