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

    Neuronpedia

    INDEX
    Explanations

    statements or reports related to a specific topic

    oai_token-act-pair · gpt-3.5-turbo

    instances of reporting or quoting statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anu
    -0.86
    ï¸
    -0.79
    estern
    -0.77
     ILCS
    -0.76
    theless
    -0.73
    otin
    -0.72
    phal
    -0.70
    odox
    -0.70
    ggles
    -0.69
    mental
    -0.69
    POSITIVE LOGITS
     goodbye
    0.91
    doms
    0.81
     earlier
    0.69
     investigators
    0.65
     chancellor
    0.63
     yesterday
    0.61
     suppliers
    0.61
     bluntly
    0.61
     previously
    0.61
     hello
    0.60
    Act Density 0.199%

    No Known Activations