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

    Neuronpedia

    INDEX
    Explanations

    phrases related to movement or transition

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating movement in and out or transitions between states or locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Terminator
    -0.63
    rieved
    -0.62
     Opening
    -0.61
     Mercy
    -0.57
     Turing
    -0.57
    090
    -0.55
    Prot
    -0.55
    bum
    -0.55
     Universal
    -0.54
    Definition
    -0.54
    POSITIVE LOGITS
    etheless
    0.86
     alike
    0.83
     metab
    0.74
     versa
    0.67
    oslav
    0.62
    igree
    0.62
     territ
    0.62
    anwhile
    0.61
     respectively
    0.60
    soDeliveryDate
    0.60
    Act Density 0.103%

    No Known Activations