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

    Neuronpedia

    INDEX
    Explanations

    phrases related to appearance or quality assessment

    oai_token-act-pair · gpt-3.5-turbo

    the verb "is" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    udeau
    -0.84
    ocobo
    -0.81
    ilst
    -0.79
    ieves
    -0.75
    sequent
    -0.71
    icipated
    -0.69
     refrain
    -0.66
     observes
    -0.66
    Others
    -0.66
    share
    -0.66
    POSITIVE LOGITS
     gonna
    1.44
     awesome
    1.15
     amazing
    1.15
     kinda
    1.15
     pretty
    1.14
     definitely
    1.13
     alright
    1.06
     awfully
    1.05
     ALWAYS
    1.04
     fucked
    1.04
    Act Density 0.533%

    No Known Activations