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

    Neuronpedia

    INDEX
    Explanations

    phrases starting with a speaker's continuation of a previous statement

    oai_token-act-pair · gpt-3.5-turbo

    repetitive phrases or structures in dialogue or narrative

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wcsstore
    -0.81
    ãĥİ
    -0.71
    Frameworks
    -0.71
    ousands
    -0.70
    eros
    -0.70
    ĪĴ
    -0.67
    arta
    -0.67
    icial
    -0.63
    士
    -0.62
    ICAN
    -0.61
    POSITIVE LOGITS
     sarcast
    1.09
     omin
    0.96
     stating
    0.95
     summar
    0.92
     noting
    0.90
     quoting
    0.90
     stressing
    0.88
     reiter
    0.87
    :]
    0.87
     bluntly
    0.85
    Act Density 0.112%

    No Known Activations