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

    Neuronpedia

    INDEX
    Explanations

    phrases related to actions of bringing or causing something to happen

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a transition or movement towards a goal or outcome

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    NING
    -0.79
    76561
    -0.72
     Wyn
    -0.71
     è£ıè¦ļéĨĴ
    -0.64
    ascript
    -0.63
    ILY
    -0.62
    estyles
    -0.60
    yip
    -0.60
    scl
    -0.59
     dx
    -0.58
    POSITIVE LOGITS
     guiActiveUnfocused
    0.78
    virt
    0.71
    anz
    0.70
    cut
    0.69
    aud
    0.68
    ordinate
    0.67
    hern
    0.66
    coming
    0.64
    GG
    0.62
    ritical
    0.61
    Act Density 0.216%

    No Known Activations