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

    Neuronpedia

    INDEX
    Explanations

    situations involving the interactions between characters in a social or legal context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .AF
    -0.16
    ãģĵãģĿ
    -0.15
    owler
    -0.15
    antee
    -0.14
    ãĥ¼ãĥ¬
    -0.14
    lassen
    -0.14
     Wing
    -0.14
    elter
    -0.14
    اÙģÛĮ
    -0.14
    aight
    -0.13
    POSITIVE LOGITS
     approached
    0.34
     approach
    0.34
    appro
    0.31
     approaches
    0.31
     Approach
    0.29
     approaching
    0.29
     подÑħод
    0.28
    Appro
    0.26
     appro
    0.25
     Appro
    0.24
    Act Density 0.389%

    No Known Activations