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

    Neuronpedia

    INDEX
    Explanations

    references to ambiguous or unspecified entities or situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    UnusedPrivate
    -0.83
    Datuak
    -0.77
     withal
    -0.63
     myſelf
    -0.61
     houſe
    -0.60
     Piso
    -0.60
     Majefty
    -0.59
     Arquivado
    -0.58
     invokingState
    -0.58
     Jefus
    -0.57
    POSITIVE LOGITS
     something
    1.56
     Something
    1.49
    something
    1.47
    Something
    1.46
     SOMETHING
    1.35
    ETHING
    1.17
     somethin
    1.13
     else
    1.11
    Somebody
    1.06
    Someone
    1.01
    Act Density 0.098%

    No Known Activations