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

    Neuronpedia

    INDEX
    Explanations

    intensity and frequency of descriptive phrases that convey strong emotional or evaluative sentiments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    onica
    -0.16
    reon
    -0.16
    olib
    -0.16
    Ñĵ
    -0.15
    olith
    -0.14
    cha
    -0.14
    ÅĻet
    -0.14
    aste
    -0.14
    idis
    -0.14
    canonical
    -0.14
    POSITIVE LOGITS
    Įĵ
    0.14
    ars
    0.14
    rina
    0.14
    stakes
    0.13
    cliffe
    0.13
    anta
    0.13
    MAND
    0.13
    881
    0.13
     tun
    0.13
    206
    0.13
    Act Density 0.062%

    No Known Activations