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

    Neuronpedia

    INDEX
    Explanations

    references to "fur" and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     century
    -0.17
    atör
    -0.16
    oire
    -0.16
    egasus
    -0.16
    sb
    -0.15
    lifting
    -0.15
    yre
    -0.15
    leine
    -0.15
    evi
    -0.14
    issing
    -0.14
    POSITIVE LOGITS
    thest
    0.25
    iously
    0.19
    thers
    0.18
    iosa
    0.18
    phy
    0.18
    fur
    0.18
    ioso
    0.17
    rowing
    0.17
    uristic
    0.17
    CAPE
    0.16
    Act Density 0.007%

    No Known Activations