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

    Neuronpedia

    INDEX
    Explanations

    words related to fundamental aspects or changes in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    statements that emphasize fundamental changes or differences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Chronicle
    -0.73
    tein
    -0.72
     supervisors
    -0.69
    ries
    -0.65
     Colleges
    -0.65
    othy
    -0.64
    andr
    -0.63
     Purchase
    -0.63
     Supervisor
    -0.62
    EVA
    -0.61
    POSITIVE LOGITS
    ãĤ´ãĥ³
    0.75
     redef
    0.72
     transforming
    0.72
     flawed
    0.72
     altering
    0.71
     resh
    0.71
     transform
    0.70
     embodied
    0.69
     unchanged
    0.69
     underpin
    0.69
    Act Density 0.007%

    No Known Activations