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

    Neuronpedia

    INDEX
    Explanations

    verbs related to actions and interactions between individuals and groups

    oai_token-act-pair · gpt-3.5-turbo

    actions and attempts made by individuals in various situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    /-
    -0.72
    inner
    -0.67
     recharge
    -0.65
     hinge
    -0.65
    definition
    -0.60
    rw
    -0.60
     arc
    -0.60
     Extend
    -0.59
    ]=
    -0.59
     depended
    -0.57
    POSITIVE LOGITS
     himself
    0.82
    reprene
    0.70
     scathing
    0.70
     tweeted
    0.68
     candid
    0.66
     his
    0.66
     onstage
    0.66
     secretly
    0.65
     famously
    0.64
    geon
    0.64
    Act Density 0.504%

    No Known Activations