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

    Neuronpedia

    INDEX
    Explanations

    words associated with feelings of satisfaction

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to feelings of satisfaction or happiness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    onut
    -0.74
    rawl
    -0.70
    nant
    -0.67
    åī
    -0.66
    ourage
    -0.65
    perm
    -0.64
    RN
    -0.64
    uli
    -0.64
     sag
    -0.62
    hem
    -0.59
    POSITIVE LOGITS
     with
    0.99
     WITH
    0.88
     withd
    0.77
     about
    0.75
     With
    0.75
    With
    0.75
    with
    0.74
     waiting
    0.72
    ient
    0.68
     wasting
    0.66
    Act Density 0.097%

    No Known Activations