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

    Neuronpedia

    INDEX
    Explanations

    large numerical values

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "ion" in various contexts, particularly in political or economic discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     cf
    -0.62
     bushes
    -0.60
     empt
    -0.59
     playbook
    -0.58
     swat
    -0.56
     thro
    -0.56
     MacDonald
    -0.56
     details
    -0.56
     Carlo
    -0.55
     clean
    -0.55
    POSITIVE LOGITS
    ION
    4.46
    IONS
    3.43
    ions
    2.58
    ion
    2.30
    ional
    1.91
    ioned
    1.67
    ione
    1.50
    IVE
    1.40
    ISON
    1.35
    ORY
    1.34
    Act Density 0.010%

    No Known Activations