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

    Neuronpedia

    INDEX
    Explanations

    positive and motivational words

    oai_token-act-pair · gpt-3.5-turbo

    positive attributes and behaviors associated with personal development and social interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     extensive
    -0.61
     bacter
    -0.60
     McDonnell
    -0.55
    Mp
    -0.54
     fasc
    -0.54
    Downloadha
    -0.53
     mac
    -0.53
     faint
    -0.53
     confirmation
    -0.53
     reapp
    -0.53
    POSITIVE LOGITS
     Yourself
    0.97
     oneself
    0.78
     srfAttach
    0.76
     yourself
    0.74
     whilst
    0.69
    enment
    0.68
    nell
    0.67
    enough
    0.66
    ¶
    0.65
     Enough
    0.64
    Act Density 0.241%

    No Known Activations