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

    Neuronpedia

    INDEX
    Explanations

    expressions of interest or curiosity in various topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    BeginContext
    -0.62
    Portale
    -0.61
    Portail
    -0.60
    roppo
    -0.56
    #
    -0.56
     cita
    -0.56
    addContainerGap
    -0.55
    chtigkeit
    -0.55
    wartet
    -0.55
     battled
    -0.55
    POSITIVE LOGITS
     interested
    2.02
    interested
    1.84
     Interested
    1.72
    Interested
    1.62
     interesado
    1.29
     concerned
    1.20
     involved
    1.14
    concerned
    1.14
    involved
    1.12
     Involved
    1.08
    Act Density 0.117%

    No Known Activations