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

    Neuronpedia

    INDEX
    Explanations

    references to the television network HBO

    oai_token-act-pair · gpt-3.5-turbo

    references to HBO and its programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    acular
    -0.84
    uation
    -0.83
    omaly
    -0.79
    acle
    -0.75
    leading
    -0.73
    uart
    -0.73
    force
    -0.72
    geant
    -0.71
    gew
    -0.70
    ional
    -0.69
    POSITIVE LOGITS
     HBO
    0.84
    EW
    0.81
    TV
    0.81
     Films
    0.79
     Mub
    0.78
     Wire
    0.75
     Networks
    0.75
    ÃįÃį
    0.75
     premiered
    0.74
    BC
    0.72
    Act Density 0.007%

    No Known Activations