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

    Neuronpedia

    INDEX
    Explanations

    words indicating potential or future possibilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    _compat
    -0.16
    umm
    -0.16
    oda
    -0.16
     kims
    -0.15
     Odds
    -0.15
    enne
    -0.14
     acl
    -0.14
    halt
    -0.14
     enough
    -0.14
    åĤ¬
    -0.13
    POSITIVE LOGITS
    /current
    0.24
    weise
    0.18
    ly
    0.17
     future
    0.17
    uture
    0.15
    mente
    0.15
    LY
    0.15
     eventual
    0.15
    SOLE
    0.15
    vig
    0.15
    Act Density 0.099%

    No Known Activations