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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating anticipation or inability to do something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nat
    -0.15
    ấp
    -0.14
    ncy
    -0.14
    974
    -0.14
    lette
    -0.14
    tern
    -0.14
    allback
    -0.13
    hod
    -0.13
     Budd
    -0.13
    emies
    -0.13
    POSITIVE LOGITS
     imagine
    0.20
     remember
    0.20
     stress
    0.19
     wait
    0.19
     WAIT
    0.19
    orque
    0.18
    remember
    0.18
     believe
    0.18
    tell
    0.17
     Guarantee
    0.17
    Act Density 0.029%

    No Known Activations