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

    Neuronpedia

    INDEX
    Explanations

    phrases related to enjoyment and participation in activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    fade
    -0.15
     Favor
    -0.14
    idelity
    -0.14
    880
    -0.13
    ftar
    -0.13
    isc
    -0.13
    ÎķΤ
    -0.13
    ÑĨвеÑĤ
    -0.13
    504
    -0.13
    oud
    -0.13
    POSITIVE LOGITS
     fun
    0.84
    fun
    0.68
     Fun
    0.68
     FUN
    0.66
    Fun
    0.64
    FUN
    0.58
    .fun
    0.56
    _fun
    0.55
    	fun
    0.54
    (fun
    0.51
    Act Density 0.139%

    No Known Activations