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

    Neuronpedia

    INDEX
    Explanations

    names starting with the letter "Ch"

    oai_token-act-pair · gpt-3.5-turbo

    repeated mentions of a specific character or name in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Vaj
    -0.66
     balloon
    -0.64
     goodwill
    -0.63
     downhill
    -0.63
     constrained
    -0.63
     unseen
    -0.59
     conditional
    -0.59
     lasting
    -0.58
     rated
    -0.57
     THR
    -0.57
    POSITIVE LOGITS
    ampion
    1.50
    ampions
    1.50
    ocolate
    1.46
    aos
    1.41
    apters
    1.41
    ambers
    1.37
    rome
    1.37
    omsky
    1.32
    rys
    1.31
    avez
    1.30
    Act Density 0.024%

    No Known Activations