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

    Neuronpedia

    INDEX
    Explanations

    phrases related to moral or ethical considerations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    StoryboardSegue
    -0.58
     Normdatei
    -0.56
     BrowserModule
    -0.53
    SourceChecksum
    -0.53
     مرئيه
    -0.51
    complexContent
    -0.50
    katapos
    -0.48
    noopener
    -0.48
    setArguments
    -0.47
    ®.
    -0.44
    POSITIVE LOGITS
     the
    0.59
    躇
    0.54
     múltiple
    0.49
    Artigo
    0.44
     táctil
    0.42
     Manusia
    0.42
     capucha
    0.40
    rrggbb
    0.40
     ancla
    0.39
     cardiaque
    0.39
    Act Density 0.601%

    No Known Activations