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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate the degree of validity or relationship of statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    entur
    -0.42
     Rakyat
    -0.40
     polig
    -0.39
    esac
    -0.39
     desti
    -0.38
    Географиясе
    -0.37
    UserScript
    -0.37
    Carrière
    -0.36
    enderror
    -0.36
    returnType
    -0.36
    POSITIVE LOGITS
     mikä
    0.59
     WHICH
    0.57
     pretty
    0.56
     Which
    0.56
     BorderRadius
    0.53
     which
    0.53
    Which
    0.52
     což
    0.52
    pretty
    0.50
     vilket
    0.50
    Act Density 0.283%

    No Known Activations