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

    Neuronpedia

    INDEX
    Explanations

    phrases related to discussing or interrogating the meaning or validity of statements

    oai_token-act-pair · gpt-3.5-turbo

    phrases that refer to the meaning or substance of concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ener
    -0.77
    erella
    -0.72
    aceae
    -0.70
    arten
    -0.70
    aire
    -0.67
    isers
    -0.66
    iets
    -0.65
    forge
    -0.64
    frog
    -0.64
    way
    -0.63
    POSITIVE LOGITS
     hostilities
    0.86
     these
    0.85
     sentences
    0.81
     this
    0.78
     those
    0.76
     each
    0.74
     events
    0.72
     prayers
    0.71
     conversations
    0.69
     sentence
    0.68
    Act Density 0.205%

    No Known Activations