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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "Rock" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    URES
    -0.78
    unctions
    -0.75
    urers
    -0.73
     aver
    -0.71
    BILITIES
    -0.67
    verages
    -0.66
    URE
    -0.66
     sidel
    -0.65
    terday
    -0.65
     practicable
    -0.65
    POSITIVE LOGITS
    ford
    1.04
    castle
    1.03
    ledge
    1.01
    star
    1.01
    cliffe
    1.00
    estone
    0.95
    ingham
    0.93
    stars
    0.93
    ete
    0.92
    well
    0.92
    Act Density 0.006%

    No Known Activations