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

    Neuronpedia

    INDEX
    Explanations

    geographical names and locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ParallelGroup
    -0.66
    ')],
    -0.64
     state
    -0.59
    ')))
    -0.57
    }$}
    -0.56
    "]))
    -0.56
    icitis
    -0.55
     \%)$
    -0.55
    invokeLater
    -0.54
    "])){
    -0.54
    POSITIVE LOGITS
     poffe
    0.69
    PreferredItem
    0.64
     pleaſure
    0.63
     naselje
    0.63
    multer
    0.62
     giusti
    0.62
     ſtre
    0.61
     Americano
    0.60
     ſhould
    0.60
     morire
    0.60
    Act Density 0.223%

    No Known Activations