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

    Neuronpedia

    INDEX
    Explanations

    phrases involving the pronoun 'we' indicating collective experiences or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cala
    -0.16
    rog
    -0.15
    ree
    -0.14
     Coh
    -0.14
    ctor
    -0.14
    wire
    -0.14
    aye
    -0.13
    resp
    -0.13
     pulse
    -0.13
    ugh
    -0.13
    POSITIVE LOGITS
    bservice
    0.18
    APON
    0.17
    eping
    0.17
    chsel
    0.16
    edy
    0.15
    athers
    0.15
    chs
    0.15
    ’re
    0.15
    epy
    0.15
    blink
    0.15
    Act Density 0.195%

    No Known Activations