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

    Neuronpedia

    INDEX
    Explanations

    aspects related to evaluations and reviews of performances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     termica
    -0.73
     Theſe
    -0.71
     Jefus
    -0.71
    mybatisplus
    -0.70
     pleaſure
    -0.69
     anún
    -0.68
     tasche
    -0.66
    <()>
    -0.66
     negroes
    -0.65
     thermique
    -0.64
    POSITIVE LOGITS
     very
    0.91
     quite
    0.83
     highly
    0.82
     extremely
    0.81
     super
    0.78
     both
    0.69
     self
    0.66
     un
    0.65
     more
    0.65
     exceptionally
    0.65
    Act Density 1.046%

    No Known Activations