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

    Neuronpedia

    INDEX
    Explanations

    phrases related to challenges or controversial issues

    oai_token-act-pair · gpt-3.5-turbo

    strong statements or claims in a discussion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ials
    -0.69
    artments
    -0.68
    yss
    -0.66
    ancers
    -0.66
    gments
    -0.63
    ants
    -0.61
    bats
    -0.61
    ummies
    -0.61
    ctors
    -0.60
    istar
    -0.60
    POSITIVE LOGITS
     nowhere
    0.82
    ģĸ
    0.80
     sorely
    0.79
    sole
    0.75
     neither
    0.75
     borne
    0.72
     underpin
    0.71
     appl
    0.71
     antit
    0.69
     nothing
    0.68
    Act Density 0.314%

    No Known Activations