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

    Neuronpedia

    INDEX
    Explanations

    words related to background information or details

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    hof
    -0.77
    ikh
    -0.73
    hap
    -0.72
    erion
    -0.72
    ora
    -0.70
    enberg
    -0.69
    atars
    -0.68
    aha
    -0.67
    rome
    -0.67
     ILCS
    -0.66
    POSITIVE LOGITS
     checks
    0.96
     Checks
    0.84
     background
    0.83
     check
    0.83
     backgrounds
    0.80
     noise
    0.74
     Background
    0.73
     Investigations
    0.73
    GROUND
    0.72
    coat
    0.71
    Act Density 0.020%

    No Known Activations