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

    Neuronpedia

    INDEX
    Explanations

    phrases related to ongoing processes or activities

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the progress or status of actions or situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    coins
    -0.73
    elo
    -0.70
    pi
    -0.67
    ene
    -0.66
    plex
    -0.66
    vere
    -0.65
     Gree
    -0.62
    Si
    -0.62
    atin
    -0.61
    rug
    -0.61
    POSITIVE LOGITS
     Caption
    0.89
    lain
    0.87
     Procedures
    0.71
    ¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯
    0.70
     Provision
    0.70
     Worldwide
    0.69
    ocument
    0.69
     courtesy
    0.69
    Condition
    0.67
     raft
    0.66
    Act Density 0.032%

    No Known Activations