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

    Neuronpedia

    INDEX
    Explanations

    references to achieving a goal or milestone

    oai_token-act-pair · gpt-3.5-turbo

    references to "stretch goals"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eer
    -0.84
    eers
    -0.82
    nect
    -0.78
    ienced
    -0.75
    eering
    -0.74
    vernment
    -0.71
    ufact
    -0.71
    izes
    -0.68
    isation
    -0.65
    hra
    -0.65
    POSITIVE LOGITS
    opian
    0.83
     stretched
    0.79
     guiActiveUnfocused
    0.75
     cred
    0.74
     lim
    0.73
     Goals
    0.73
    bean
    0.70
     stretches
    0.69
    onge
    0.68
     Armstrong
    0.66
    Act Density 0.046%

    No Known Activations