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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the verification and privacy of Facebook accounts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lainen
    -0.50
    ConstraintMaker
    -0.46
    owna
    -0.45
    TemporalType
    -0.44
     незавершена
    -0.44
    ništvo
    -0.44
     Juan
    -0.43
    Juan
    -0.43
    TagMode
    -0.43
    Демографія
    -0.42
    POSITIVE LOGITS
    жного
    0.46
    vaného
    0.41
    ного
    0.41
    чного
    0.40
    ého
    0.40
    cego
    0.39
    thâu
    0.39
    тельного
    0.39
    ского
    0.39
    ného
    0.39
    Act Density 0.116%

    No Known Activations