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

    Neuronpedia

    INDEX
    Explanations

    phrases related to judgment or evaluation

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating mistakes or misconceptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ahime
    -0.87
    edia
    -0.77
    prus
    -0.63
    earcher
    -0.62
    bsite
    -0.61
     nearest
    -0.60
    odore
    -0.60
    rique
    -0.60
     [|
    -0.60
    ellow
    -0.59
    POSITIVE LOGITS
     except
    1.03
    together
    0.96
     together
    0.90
     facets
    0.76
     toget
    0.75
     revolves
    0.73
     alike
    0.71
    opathic
    0.69
    oots
    0.68
    except
    0.66
    Act Density 0.183%

    No Known Activations