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

    Neuronpedia

    INDEX
    Explanations

    phrases that express potential or capability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Dumpster
    -0.16
    Disposed
    -0.15
    avenport
    -0.14
    entin
    -0.14
     Åŀehir
    -0.14
     Benton
    -0.14
    439
    -0.14
    .mdl
    -0.14
    enti
    -0.14
    ç²Ĵ
    -0.14
    POSITIVE LOGITS
     possibly
    0.31
     possible
    0.29
     Possibly
    0.26
    possibly
    0.26
     POSS
    0.26
    possible
    0.24
     Possible
    0.23
    åı¯èĥ½
    0.23
    _possible
    0.23
    Possible
    0.22
    Act Density 0.056%

    No Known Activations