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

    Neuronpedia

    INDEX
    Explanations

    terms related to instinctive behaviors and responses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    isoft
    -0.19
    idge
    -0.17
    ÏĦÏī
    -0.15
    ulet
    -0.15
    itore
    -0.15
    ikut
    -0.15
    lsen
    -0.15
    auc
    -0.14
    asso
    -0.14
    cip
    -0.14
    POSITIVE LOGITS
    ively
    0.18
    aneously
    0.16
    aneous
    0.15
    ieri
    0.15
    ROID
    0.15
    omin
    0.15
    apes
    0.14
    less
    0.14
    x
    0.14
    uous
    0.14
    Act Density 0.010%

    No Known Activations