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

    Neuronpedia

    INDEX
    Explanations

    statements related to legal and political discussions

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate concern or mention of family and community issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    chnology
    -0.74
    obos
    -0.71
    edge
    -0.69
    sword
    -0.66
    osite
    -0.65
    perture
    -0.65
    inctions
    -0.63
    eret
    -0.62
    ebus
    -0.60
    Forge
    -0.59
    POSITIVE LOGITS
    âĢ
    1.25
    said
    1.05
     âĢ
    1.02
     says
    1.00
    »
    0.98
     said
    0.98
    ãĢ
    0.96
     huh
    0.91
    ``
    0.91
     according
    0.89
    Act Density 0.232%

    No Known Activations