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

    Neuronpedia

    INDEX
    Explanations

    expressions of positive emotions or sentiments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     للمعارف
    -0.63
     houſe
    -0.60
    DockStyle
    -0.57
    ThroughAttribute
    -0.56
    TimerTask
    -0.56
     lugs
    -0.51
     estekak
    -0.51
    divarius
    -0.50
     tolua
    -0.49
    durante
    -0.49
    POSITIVE LOGITS
     sekali
    0.59
     about
    0.59
    లాలు
    0.59
     they
    0.58
     to
    0.52
     över
    0.50
    ValueStyle
    0.50
     we
    0.49
     that
    0.49
    ádza
    0.49
    Act Density 0.065%

    No Known Activations