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

    Neuronpedia

    INDEX
    Explanations

    phrases related to significant analysis or evaluations in research contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     fitt
    -0.54
     throats
    -0.48
     dunno
    -0.46
    FFFF
    -0.46
     blah
    -0.46
     downed
    -0.45
     helicop
    -0.44
    tein
    -0.44
     swapped
    -0.44
     Likes
    -0.44
    POSITIVE LOGITS
    ¶
    0.63
    phal
    0.58
     regarding
    0.56
     illustrating
    0.54
     concerning
    0.52
    0.50
    actionDate
    0.49
     empir
    0.48
    AUT
    0.47
    DragonMagazine
    0.47
    Act Density 0.712%

    No Known Activations