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

    Neuronpedia

    INDEX
    Explanations

    hyphenated words or phrases indicating a connection or involvement between parties

    oai_token-act-pair · gpt-3.5-turbo

    references to US-led actions or initiatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Grimes
    -0.86
     Dickinson
    -0.83
     Aval
    -0.77
     showers
    -0.76
     shelf
    -0.73
     shower
    -0.67
     Melvin
    -0.66
    plin
    -0.65
     cir
    -0.65
     beetles
    -0.64
    POSITIVE LOGITS
    style
    1.19
    induced
    1.18
    centric
    1.18
    controlled
    1.15
    dominated
    1.11
    friendly
    1.10
    backed
    1.09
    inspired
    1.09
    driven
    1.07
    imposed
    1.06
    Act Density 0.080%

    No Known Activations