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

    Neuronpedia

    INDEX
    Explanations

    words related to uplifting or inspiring moments

    oai_token-act-pair · gpt-3.5-turbo

    words related to elevation and descent, particularly in emotional or situational contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Cola
    -0.68
     Electronic
    -0.67
    POL
    -0.65
    PRES
    -0.65
     Thief
    -0.65
     Heller
    -0.64
     Hague
    -0.63
    BOOK
    -0.63
     Continued
    -0.63
     Fiscal
    -0.63
    POSITIVE LOGITS
    ifted
    1.18
    ifting
    1.06
    ift
    1.04
     upl
    1.00
    itud
    0.97
    ongs
    0.93
    atters
    0.90
    ands
    0.89
    ifts
    0.88
    ains
    0.88
    Act Density 0.008%

    No Known Activations