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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a departure or end of something

    oai_token-act-pair · gpt-3.5-turbo

    directional or positional terms related to movement and location

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Vaugh
    -0.67
     Palestin
    -0.66
    athan
    -0.59
     Kahn
    -0.57
     Naz
    -0.56
     Nev
    -0.55
     Nare
    -0.54
     Gilbert
    -0.53
     Azerb
    -0.51
     Holl
    -0.51
    POSITIVE LOGITS
     ][
    0.83
    lishes
    0.74
     +=
    0.71
    tics
    0.69
     :=
    0.68
    redients
    0.67
    Joined
    0.66
    lined
    0.64
    malink
    0.64
    cro
    0.64
    Act Density 0.080%

    No Known Activations