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

    Neuronpedia

    INDEX
    Explanations

    references to respect and its related concepts in interpersonal or societal contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    antry
    -0.19
    opard
    -0.17
    elim
    -0.15
    elop
    -0.15
    argout
    -0.15
    zbollah
    -0.15
    Exposed
    -0.15
    ichtet
    -0.15
    hop
    -0.15
    Descriptor
    -0.14
    POSITIVE LOGITS
    ively
    0.38
    ably
    0.29
    ability
    0.29
    fulness
    0.26
    ors
    0.24
    ible
    0.24
    uous
    0.24
    full
    0.23
    ful
    0.22
    ivity
    0.21
    Act Density 0.040%

    No Known Activations