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

    Neuronpedia

    INDEX
    Explanations

    conjunctive phrases and contrasting transitions in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     supposed
    -0.52
    supposed
    -0.49
     favourably
    -0.48
     Trip
    -0.45
     bagus
    -0.45
     safe
    -0.43
     flourishing
    -0.43
    比較的
    -0.42
     hopeful
    -0.42
     Verhältnis
    -0.42
    POSITIVE LOGITS
    GEBURTSDATUM
    0.83
     NSCoder
    0.70
    AddressBook
    0.69
    ंदीखरीदारी
    0.68
    הערות
    0.67
     autorytatywna
    0.66
     consultato
    0.64
     للاسماء
    0.63
     Normdatei
    0.62
     OMITBAD
    0.61
    Act Density 0.377%

    No Known Activations