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

    Neuronpedia

    INDEX
    Explanations

    names of cities or locations

    oai_token-act-pair · gpt-3.5-turbo

    names of individuals or entities, particularly in a sports context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Reviewer
    -0.58
     unfavorable
    -0.53
    ailable
    -0.52
    âĸĵ
    -0.50
     hindsight
    -0.50
     rather
    -0.48
     differently
    -0.47
     pleas
    -0.47
     glim
    -0.47
     Adin
    -0.47
    POSITIVE LOGITS
     Islands
    0.63
     âĵĺ
    0.62
     etc
    0.61
     TBA
    0.60
     Univ
    0.60
     &
    0.56
    ;;;;;;;;;;;;
    0.56
    tone
    0.53
    esan
    0.52
     Tone
    0.51
    Act Density 0.663%

    No Known Activations