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

    Neuronpedia

    INDEX
    Explanations

    phrases related to intense emotions or situations

    oai_token-act-pair · gpt-3.5-turbo

    ellipses or pauses in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     merit
    -0.74
    opath
    -0.69
     attest
    -0.67
     scapego
    -0.64
     wielded
    -0.64
     heaviest
    -0.64
     replacement
    -0.63
     complement
    -0.63
     depletion
    -0.62
     adulthood
    -0.62
    POSITIVE LOGITS
    BUT
    1.09
    yet
    1.06
    why
    1.05
    until
    1.05
    oops
    1.02
    except
    0.97
    yeah
    0.97
    unless
    0.96
    whatever
    0.96
    they
    0.95
    Act Density 0.044%

    No Known Activations