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

    Neuronpedia

    INDEX
    Explanations

    statements about the main focus or purpose of a situation or topic

    oai_token-act-pair · gpt-3.5-turbo

    statements regarding the nature and significance of various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ingham
    -0.78
    emale
    -0.69
    aris
    -0.69
    ordes
    -0.68
    ĭ
    -0.66
    ¢
    -0.65
    edient
    -0.64
    arin
    -0.63
    ente
    -0.63
    arb
    -0.62
    POSITIVE LOGITS
     about
    1.96
    about
    1.88
     ABOUT
    1.78
     About
    1.74
    About
    1.53
     regarding
    1.19
     concerning
    1.12
    abouts
    1.07
     Regarding
    1.01
     bout
    0.97
    Act Density 0.260%

    No Known Activations