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

    Neuronpedia

    INDEX
    Explanations

    phrases related to conditional probability and inference in statistics

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Roskov
    -0.73
     Jennings
    -0.70
     Situation
    -0.68
    stasis
    -0.68
    Situation
    -0.68
     SITUATION
    -0.67
     conditions
    -0.66
     situation
    -0.66
     Exacts
    -0.65
    htdocs
    -0.65
    POSITIVE LOGITS
     conditional
    1.09
    conditional
    1.09
     Conditional
    1.09
    Conditional
    1.04
     conditionally
    0.82
    IndentedString
    0.76
     unconditional
    0.75
    ftagPool
    0.73
     Dunkel
    0.68
    kiel
    0.64
    Act Density 0.006%

    No Known Activations