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

    Neuronpedia

    INDEX
    Explanations

    assertive statements or claims about situations and events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     <=",
    -0.96
     nahilalakip
    -0.84
    
    -0.80
     kaarangay
    -0.77
    Composable
    -0.76
    AndEndTag
    -0.74
    ThroughAttribute
    -0.65
    исленность
    -0.64
    Прият
    -0.62
    ContentAlignment
    -0.62
    POSITIVE LOGITS
     incredible
    1.52
     unbelievable
    1.45
     amazing
    1.44
     phenomenal
    1.44
     extraordinary
    1.39
     astounding
    1.36
     AMAZING
    1.30
     astonishing
    1.29
     Incredible
    1.26
    incredible
    1.25
    Act Density 0.404%

    No Known Activations