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

    Neuronpedia

    INDEX
    Explanations

    references to spatial or situational contexts within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     behalf
    -0.16
    917
    -0.15
     ÑĤÑĢÑĥд
    -0.14
     barely
    -0.14
    åħ¨åĽ½
    -0.13
    太éĥİ
    -0.13
     everywhere
    -0.13
    subj
    -0.13
     Various
    -0.13
    opers
    -0.13
    POSITIVE LOGITS
     situations
    0.37
     cases
    0.35
     certain
    0.33
     instances
    0.33
    cases
    0.32
     circumstances
    0.26
    instances
    0.26
     certains
    0.26
    Certain
    0.25
     Certain
    0.24
    Act Density 0.337%

    No Known Activations