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

    Neuronpedia

    INDEX
    Explanations

    names or references to people from various locations

    oai_token-act-pair · gpt-3.5-turbo

    the presence of the name "Je" and its variations in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    grounds
    -0.71
    Interstitial
    -0.70
    izoph
    -0.66
     CPC
    -0.66
     allowable
    -0.66
    sound
    -0.64
    norm
    -0.63
    heartedly
    -0.62
     Defin
    -0.62
    Ast
    -0.61
    POSITIVE LOGITS
    je
    1.40
    Å¡
    0.98
    opard
    0.97
    lda
    0.96
    ja
    0.94
    ek
    0.93
    eling
    0.92
    orge
    0.91
    zza
    0.89
    lde
    0.89
    Act Density 0.004%

    No Known Activations