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

    Neuronpedia

    INDEX
    Explanations

    verbs related to defending or protection

    oai_token-act-pair · gpt-3.5-turbo

    references to acts of defense or justification

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ombies
    -0.72
    FORE
    -0.68
    orld
    -0.65
    7601
    -0.64
    hook
    -0.62
    RESULTS
    -0.61
    Chart
    -0.61
    tail
    -0.61
    owler
    -0.59
    ppa
    -0.59
    POSITIVE LOGITS
     against
    1.33
    against
    1.13
     Against
    1.13
     vigorously
    1.00
     indef
    0.97
    atively
    0.83
    iveness
    0.82
    ively
    0.81
     AGA
    0.75
     forcefully
    0.74
    Act Density 0.057%

    No Known Activations