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

    Neuronpedia

    INDEX
    Explanations

    phrases related to programming functions and their expected outcomes

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    laris
    -0.47
     support
    -0.47
    verwijspagina
    -0.47
     oma
    -0.47
    github
    -0.45
     juli
    -0.45
     custom
    -0.44
    anas
    -0.44
     transfieras
    -0.43
    Erf
    -0.43
    POSITIVE LOGITS
     Italijanski
    0.69
     poffible
    0.65
     $_"
    0.64
    IsMutable
    0.64
     abstrato
    0.63
     reaſon
    0.63
     itſelf
    0.61
     myſelf
    0.61
     themſelves
    0.60
    msgSender
    0.60
    Act Density 0.040%

    No Known Activations