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

    Neuronpedia

    INDEX
    Explanations

    last-minute decisions or actions

    oai_token-act-pair · gpt-3.5-turbo

    references to urgency or last-minute actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    WAR
    -0.87
    MAT
    -0.80
    ashtra
    -0.80
    avia
    -0.73
    MEN
    -0.72
    RW
    -0.72
    Rust
    -0.70
     Mothers
    -0.70
    shall
    -0.70
    Rad
    -0.70
    POSITIVE LOGITS
    aneously
    0.84
     cancell
    0.82
     sequencing
    0.82
     scramble
    0.81
     preparations
    0.79
     maneuver
    0.79
     ambush
    0.77
     additions
    0.76
    imester
    0.76
     messenger
    0.72
    Act Density 0.026%

    No Known Activations