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

    Neuronpedia

    INDEX
    Explanations

    phrases encouraging action or engagement, particularly through giving feedback or making calls

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ibase
    -0.16
    rd
    -0.16
    edii
    -0.16
    ogie
    -0.15
    aler
    -0.15
    rb
    -0.14
    ophil
    -0.14
     Ard
    -0.14
    orre
    -0.13
    137
    -0.13
    POSITIVE LOGITS
     Decompiled
    0.16
    λει
    0.15
    ÃŃs
    0.15
     HEAP
    0.14
    YES
    0.14
    houses
    0.14
    FAIL
    0.14
    bul
    0.14
    æĶ
    0.14
    imps
    0.14
    Act Density 0.036%

    No Known Activations