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

    Neuronpedia

    INDEX
    Explanations

    phrases that convey intentions or actions related to future plans

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     zelve
    -0.83
     Nestor
    -0.82
     Prisma
    -0.80
     Mapp
    -0.79
    IsContent
    -0.78
     Ise
    -0.77
    EnumMember
    -0.76
    prechpartner
    -0.75
     stöd
    -0.75
     isolado
    -0.74
    POSITIVE LOGITS
     gonna
    1.17
     Gonna
    1.14
    Gonna
    1.14
     GONNA
    1.13
    gonna
    1.03
     wanna
    0.93
     gotta
    0.84
     want
    0.77
     Wanna
    0.74
     fucking
    0.74
    Act Density 0.063%

    No Known Activations