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

    Neuronpedia

    INDEX
    Explanations

    phrases that emphasize the concept of connection or relatedness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Theſe
    -0.79
    orexia
    -0.76
    namental
    -0.74
    zembro
    -0.74
    cześ
    -0.73
    noons
    -0.73
    ^(@)
    -0.72
    quele
    -0.71
    volving
    -0.70
    PostExecute
    -0.68
    POSITIVE LOGITS
    {{{
    0.53
    schung
    0.52
    S
    0.51
     censo
    0.49
    ype
    0.48
    RegistryLite
    0.47
    日閲覧
    0.47
    nn
    0.45
    mingen
    0.45
    she
    0.45
    Act Density 0.269%

    No Known Activations