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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate the central essence or core issues of a topic

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oler
    -0.15
    usan
    -0.15
    ahlen
    -0.15
    -gnu
    -0.15
    sez
    -0.14
    mlin
    -0.14
    /hooks
    -0.14
    iem
    -0.13
    ista
    -0.13
    owers
    -0.13
    POSITIVE LOGITS
     core
    0.38
    core
    0.32
    (core
    0.28
    -core
    0.28
     heart
    0.27
    _core
    0.25
    /Core
    0.25
    .core
    0.25
    /core
    0.25
     Core
    0.25
    Act Density 0.110%

    No Known Activations