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

    Neuronpedia

    INDEX
    Explanations

    phrases related to involvement or participation in various activities

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "engage" and its variations in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ahon
    -0.67
    pler
    -0.67
     overrun
    -0.63
    dylib
    -0.61
     confir
    -0.56
    DragonMagazine
    -0.56
     Printed
    -0.56
    atto
    -0.55
     scattering
    -0.55
    ough
    -0.55
    POSITIVE LOGITS
    ments
    0.91
    ingly
    0.80
     with
    0.78
     actively
    0.76
    ienced
    0.76
    igate
    0.73
    antically
    0.73
    TAIN
    0.73
    ment
    0.70
     hostilities
    0.70
    Act Density 0.030%

    No Known Activations