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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing positive emotions or feelings

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to positive experiences and feelings of accomplishment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    soever
    -0.70
    é¾įå¥ij士
    -0.70
     Preferences
    -0.65
    anooga
    -0.65
    ãĤ¦ãĤ¹
    -0.65
    furt
    -0.64
    aneous
    -0.64
    ©¶æ¥µ
    -0.62
    uria
    -0.62
    natureconservancy
    -0.62
    POSITIVE LOGITS
     see
    1.20
     hear
    1.19
     finally
    1.05
     behold
    1.05
     know
    1.03
     realize
    1.00
     have
    0.99
     be
    0.98
     watch
    0.98
     realise
    0.95
    Act Density 0.091%

    No Known Activations