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

    Neuronpedia

    INDEX
    Explanations

    issues related to personal relationships and introspection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     fué
    -0.80
     habia
    -0.52
     piú
    -0.49
     terminée
    -0.44
     étoit
    -0.42
     tambien
    -0.40
     eenig
    -0.40
     poichè
    -0.39
     Schluß
    -0.39
     auroit
    -0.39
    POSITIVE LOGITS
     Normdatei
    0.85
    MessageOf
    0.78
     surla
    0.75
    httphttps
    0.69
     ISNI
    0.69
     ModelExpression
    0.67
    <_>
    0.65
     actives
    0.65
    JspWriter
    0.64
    lishes
    0.64
    Act Density 0.622%

    No Known Activations