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

    Neuronpedia

    INDEX
    Explanations

    phrases and words related to collaboration and partnerships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arem
    -0.17
    ouz
    -0.17
     Ñģо
    -0.17
    ĶĶ
    -0.17
    ysl
    -0.15
    mans
    -0.15
    ôm
    -0.15
    (with
    -0.15
    mens
    -0.15
    rm
    -0.14
    POSITIVE LOGITS
     wt
    0.26
     iw
    0.24
     wi
    0.23
     wir
    0.23
     Willi
    0.21
     wid
    0.21
     ith
    0.20
     whit
    0.19
     Wit
    0.19
     will
    0.19
    Act Density 0.150%

    No Known Activations