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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating first-time experiences or debuts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aarrggbb
    -0.56
    Климат
    -0.49
    +#+
    -0.46
     Slack
    -0.42
    Mutagenicity
    -0.40
    ęty
    -0.40
     lý
    -0.39
    立て
    -0.39
     Mob
    -0.39
    MOD
    -0.39
    POSITIVE LOGITS
     nahilalakip
    0.89
    Rujuakan
    0.84
     debut
    0.79
    debut
    0.79
    脚注の使い方
    0.78
    Carriera
    0.75
    Debut
    0.74
    fjspx
    0.72
    GEBURTS
    0.72
     MainAxisSize
    0.71
    Act Density 0.149%

    No Known Activations