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

    Neuronpedia

    INDEX
    Explanations

    phrases related to opening something physically or figuratively

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "open" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     endors
    -0.69
    Sov
    -0.63
     Reform
    -0.61
    VICE
    -0.61
    Param
    -0.59
    Bey
    -0.59
    ty
    -0.58
     disband
    -0.57
     footing
    -0.57
    zik
    -0.57
    POSITIVE LOGITS
    acles
    0.89
     doors
    0.88
     jaws
    0.82
    tained
    0.80
    ococ
    0.79
     wounds
    0.77
     pores
    0.76
     parentheses
    0.75
    taining
    0.74
     drawer
    0.74
    Act Density 0.063%

    No Known Activations