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

    Neuronpedia

    INDEX
    Explanations

    phrases related to progression or movement

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating progression or movement towards a goal

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     variance
    -0.64
     Warrant
    -0.64
     includ
    -0.64
    Synopsis
    -0.64
     variation
    -0.59
    reau
    -0.59
     accompanying
    -0.57
    unit
    -0.57
     activ
    -0.57
     spare
    -0.57
    POSITIVE LOGITS
     adulthood
    0.96
    enhagen
    0.91
    livion
    0.89
     brink
    0.88
     adolescence
    0.81
     heights
    0.81
     fruition
    0.80
    alach
    0.79
     sidx
    0.77
    iphany
    0.76
    Act Density 0.470%

    No Known Activations