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

    Neuronpedia

    INDEX
    Explanations

    phrases related to actions and characteristics of individuals

    oai_token-act-pair · gpt-3.5-turbo

    non-unique transitional phrases and expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ¬¼
    -0.72
    UF
    -0.71
    eus
    -0.69
    izen
    -0.69
    ¥
    -0.67
    enary
    -0.66
    ½
    -0.66
    =#
    -0.64
    chell
    -0.64
    reprene
    -0.64
    POSITIVE LOGITS
     though
    1.13
     however
    1.08
     albeit
    1.04
     but
    1.02
     although
    1.01
     whereas
    0.93
     meanwhile
    0.88
     especially
    0.86
     including
    0.86
     which
    0.80
    Act Density 0.621%

    No Known Activations