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

    Neuronpedia

    INDEX
    Explanations

    verbs related to actions or changes happening to something

    oai_token-act-pair · gpt-3.5-turbo

    verbs and phrases indicating support or compensatory actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    !,
    -0.50
    ngth
    -0.49
    !/
    -0.46
     thriller
    -0.46
    Ħ¢
    -0.46
     Beautiful
    -0.45
     Spotlight
    -0.45
    !.
    -0.44
     worldwide
    -0.43
     POLITICO
    -0.43
    POSITIVE LOGITS
    kees
    0.57
    rin
    0.55
    arat
    0.50
    chal
    0.48
    ãĥĹ
    0.47
    eenth
    0.46
    ying
    0.46
    rd
    0.45
    fitting
    0.44
    aran
    0.44
    Act Density 0.822%

    No Known Activations