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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating applicability or inclusion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Bened
    -0.16
    IBC
    -0.14
    ijk
    -0.14
     Ap
    -0.14
     twice
    -0.14
    mah
    -0.14
     Stanley
    -0.13
     Nun
    -0.13
     spare
    -0.13
    ħ
    -0.13
    POSITIVE LOGITS
    ombo
    0.15
    ernaut
    0.15
    Writes
    0.14
    azzo
    0.14
    olatile
    0.14
    orm
    0.14
    %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
    0.14
    amerate
    0.14
    AsyncResult
    0.13
    oyo
    0.13
    Act Density 0.010%

    No Known Activations