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

    Neuronpedia

    INDEX
    Explanations

    expressions of positive sentiments or feelings of gratitude

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     noDo
    -0.50
     Autorizaciones
    -0.44
    ècie
    -0.43
    出版年
    -0.41
    Cyfarwyddwr
    -0.41
     Arkivert
    -0.41
     Italijanski
    -0.40
     voici
    -0.39
     мәкал
    -0.38
    &__
    -0.37
    POSITIVE LOGITS
    SequentialGroup
    0.54
    endphp
    0.50
     gratifying
    0.47
    Прият
    0.45
     Überras
    0.44
     surprising
    0.44
    omitempty
    0.44
    CodeAttribute
    0.44
    addGap
    0.42
     känns
    0.42
    Act Density 0.339%

    No Known Activations