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

    Neuronpedia

    INDEX
    Explanations

    verbs associated with calling upon or bringing forth something or someone

    oai_token-act-pair · gpt-3.5-turbo

    references to calling forth or invoking entities or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hirt
    -0.76
    sonian
    -0.75
    cas
    -0.74
    abet
    -0.73
    ians
    -0.69
    estyles
    -0.66
    hops
    -0.66
    mys
    -0.65
    itarian
    -0.65
    ©¶æ
    -0.64
    POSITIVE LOGITS
     wrath
    0.91
     summon
    0.80
    eer
    0.78
     summoning
    0.77
     Cth
    0.76
     indignation
    0.76
     invoked
    0.76
    eers
    0.75
    uncture
    0.75
     demons
    0.74
    Act Density 0.114%

    No Known Activations