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

    Neuronpedia

    INDEX
    Explanations

    numeric patterns or sequences, especially involving dashes or numerical arrangements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     zelve
    -0.55
    ьаж
    -0.49
     zijne
    -0.48
    astify
    -0.46
    rrggbb
    -0.44
    ioutil
    -0.43
     cultuur
    -0.43
    TemporalType
    -0.42
    ècie
    -0.42
    примеча
    -0.41
    POSITIVE LOGITS
     Meilleur
    0.44
     short
    0.42
    曖昧さ回避
    0.41
     prs
    0.40
    -(-
    0.40
     chips
    0.40
     ब्रेकडाउन
    0.40
     TNT
    0.40
     fhort
    0.40
     shortest
    0.39
    Act Density 0.488%

    No Known Activations