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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating movement in and out

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to movement or transitions in and out of places

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Rite
    -0.73
    atl
    -0.69
     Canyon
    -0.66
    than
    -0.66
     Kali
    -0.65
    iom
    -0.63
     Sense
    -0.62
    512
    -0.61
     Trouble
    -0.61
    /#
    -0.60
    POSITIVE LOGITS
    =-=-=-=-=-=-=-=-
    0.76
    senal
    0.75
     alike
    0.71
     metab
    0.70
    scill
    0.66
    anwhile
    0.64
     emergencies
    0.62
    )=(
    0.61
     leaflets
    0.60
    rely
    0.60
    Act Density 0.084%

    No Known Activations