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

    Neuronpedia

    INDEX
    Explanations

    verbs or phrases related to the inability to verify something or uncertain situations

    oai_token-act-pair · gpt-3.5-turbo

    phrases that emphasize the concept of "being" or existence in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rongh
    -0.62
     mull
    -0.62
    lique
    -0.62
    linger
    -0.61
     CFR
    -0.59
    igl
    -0.58
     sheriff
    -0.58
     flock
    -0.58
    ollah
    -0.58
    court
    -0.58
    POSITIVE LOGITS
     anymore
    0.98
    uate
    0.81
    ĵĺ
    0.81
    athom
    0.79
     nor
    0.78
     anything
    0.72
     adequately
    0.72
    ̶
    0.72
    @@@@
    0.71
     satisf
    0.70
    Act Density 0.213%

    No Known Activations