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

    Neuronpedia

    INDEX
    Explanations

    actions related to helping or supporting others

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to significant achievements and helping others

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ħ¢
    -0.57
    onto
    -0.56
    onga
    -0.55
    mite
    -0.55
    %.
    -0.53
    idi
    -0.53
    stones
    -0.52
     deems
    -0.51
    pmwiki
    -0.51
    Pic
    -0.51
    POSITIVE LOGITS
     Byr
    0.61
     yesterday
    0.56
     Nixon
    0.56
     voic
    0.53
     awaken
    0.52
     Yanuk
    0.51
     initially
    0.51
     Uriel
    0.50
     earlier
    0.49
     intending
    0.49
    Act Density 2.627%

    No Known Activations