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

    Neuronpedia

    INDEX
    Explanations

    instances and examples to support arguments or statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    unes
    -0.59
     See
    -0.50
    See
    -0.49
     Va
    -0.46
     desired
    -0.45
     there
    -0.45
     We
    -0.42
     see
    -0.42
     There
    -0.41
    R
    -0.41
    POSITIVE LOGITS
     MainAxisSize
    0.87
    +#+#
    0.86
    rungsseite
    0.82
    StoryboardSegue
    0.82
     TestBed
    0.79
     nakalista
    0.77
    UserScript
    0.77
     ligiloj
    0.77
    Personendaten
    0.76
     ControllerBase
    0.76
    Act Density 0.253%

    No Known Activations