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

    Neuronpedia

    INDEX
    Explanations

    references to specific people, particularly names and familial relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    othelioma
    -0.53
     igång
    -0.51
    σθαι
    -0.50
    aronder
    -0.49
     gesteld
    -0.48
    jahtera
    -0.47
     contextLoads
    -0.46
    ppling
    -0.46
    buie
    -0.46
    TagMode
    -0.46
    POSITIVE LOGITS
    ########.
    0.51
     ModelExpression
    0.49
    __':
    0.47
     dad
    0.44
    httphttps
    0.39
    Dad
    0.39
    __":
    0.39
     brother
    0.39
    <?
    0.38
     bhai
    0.38
    Act Density 0.527%

    No Known Activations