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

    Neuronpedia

    INDEX
    Explanations

    expressions of positive sentiments and enjoyment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ensibly
    -0.16
    869
    -0.15
    kip
    -0.15
    ãĥ©ãĥĥãĤ¯
    -0.15
     Allan
    -0.14
     hyp
    -0.14
    roj
    -0.14
    论
    -0.14
    odem
    -0.14
    RIES
    -0.14
    POSITIVE LOGITS
    emma
    0.16
    astle
    0.16
    midt
    0.15
    tingham
    0.15
    ernal
    0.14
    inear
    0.14
    OLER
    0.14
    rn
    0.14
    ARRIER
    0.14
    onnen
    0.14
    Act Density 0.118%

    No Known Activations