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

    Neuronpedia

    INDEX
    Explanations

    phrases related to halting or stopping actions or progress

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express interruptions or calls to halt actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    soDeliveryDate
    -0.75
    ebus
    -0.71
     deserts
    -0.63
    icol
    -0.62
    uld
    -0.62
    tools
    -0.61
    KNOWN
    -0.59
    properties
    -0.59
    nai
    -0.59
    STEM
    -0.58
    POSITIVE LOGITS
    motion
    0.78
    ãĤ®
    0.76
     bleeding
    0.73
    steen
    0.71
    301
    0.64
    Production
    0.63
    755
    0.63
     sidew
    0.62
     movement
    0.62
     bothering
    0.61
    Act Density 0.135%

    No Known Activations