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

    Neuronpedia

    INDEX
    Explanations

    terms related to temporal phrases and contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Autoritní
    -0.81
     createSlice
    -0.77
    expandindo
    -0.70
     CreateTagHelper
    -0.67
    脚注の使い方
    -0.65
    -0.59
    utrients
    -0.57
    twimg
    -0.57
     autorytatywna
    -0.56
    homonymie
    -0.55
    POSITIVE LOGITS
     situations
    1.12
     certain
    0.98
     instances
    0.90
     certains
    0.85
     Situations
    0.85
     certaines
    0.85
     vissa
    0.84
     cases
    0.84
     situaciones
    0.81
     CERTAIN
    0.81
    Act Density 0.658%

    No Known Activations