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

    Neuronpedia

    INDEX
    Explanations

    verbs related to actions of pulling or removing something

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "pluck" and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     reckoning
    -0.61
     refuel
    -0.60
     chilled
    -0.60
    bring
    -0.59
     rapt
    -0.59
     bartender
    -0.59
    zig
    -0.58
     epoch
    -0.58
    famous
    -0.57
    Zen
    -0.57
    POSITIVE LOGITS
    IONS
    0.79
    enary
    0.76
    ibilities
    0.75
    ions
    0.74
    acter
    0.72
    ACE
    0.71
    ainer
    0.70
    ATIONS
    0.68
    inational
    0.68
    ion
    0.66
    Act Density 0.121%

    No Known Activations