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

    Neuronpedia

    INDEX
    Explanations

    key terms and phrases that indicate conditional or hypothetical scenarios

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rove
    -0.16
    okol
    -0.16
    edl
    -0.15
     bý
    -0.15
    ingleton
    -0.15
    ennon
    -0.15
    HCI
    -0.15
    _fwd
    -0.14
     principalTable
    -0.14
    abo
    -0.14
    POSITIVE LOGITS
    egg
    0.18
    ipping
    0.17
    essay
    0.16
    inox
    0.15
    sb
    0.15
    iox
    0.14
    yssey
    0.13
     Platform
    0.13
    ise
    0.13
    esson
    0.13
    Act Density 0.014%

    No Known Activations