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

    Neuronpedia

    INDEX
    Explanations

    phrases related to reaching a certain level or point

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating levels or milestones that have been achieved or reached

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vich
    -0.69
    hair
    -0.66
     EVENTS
    -0.66
    gay
    -0.66
    cour
    -0.64
    handler
    -0.63
    bus
    -0.62
    wcsstore
    -0.62
     includ
    -0.62
    strong
    -0.61
    POSITIVE LOGITS
     saturation
    1.16
     puberty
    1.06
     maturity
    1.05
     equilibrium
    1.05
     parity
    1.05
     heights
    1.00
     exhaustion
    0.96
     climax
    0.95
     peak
    0.94
     fruition
    0.93
    Act Density 0.122%

    No Known Activations