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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating disagreement or opposition to certain beliefs or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     o
    -0.15
    æº
    -0.15
    æĤ
    -0.15
    .registry
    -0.14
    µ
    -0.14
    κο
    -0.14
    roperty
    -0.14
    hausen
    -0.14
    dex
    -0.14
     hail
    -0.14
    POSITIVE LOGITS
    Argb
    0.20
    icient
    0.19
    elan
    0.18
    acket
    0.17
     žal
    0.16
    pii
    0.16
    ISR
    0.15
    495
    0.15
    akis
    0.15
    ackets
    0.15
    Act Density 0.078%

    No Known Activations