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

    Neuronpedia

    INDEX
    Explanations

    names of newspapers or publications

    oai_token-act-pair · gpt-3.5-turbo

    references to specific media outlets and notable individuals involved in news reporting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    icum
    -0.82
    ctica
    -0.76
    antha
    -0.71
    orney
    -0.69
    ĪĴ
    -0.69
    culus
    -0.68
     sailors
    -0.68
    ilion
    -0.67
    ouston
    -0.67
    othes
    -0.67
    POSITIVE LOGITS
     Spiegel
    1.06
    iegel
    0.99
    enstein
    0.99
    mann
    0.90
     Schwarz
    0.85
    stein
    0.84
     Fein
    0.82
    man
    0.81
    baum
    0.81
    wald
    0.81
    Act Density 0.013%

    No Known Activations