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

    Neuronpedia

    INDEX
    Explanations

    strings with the substring 'str' followed by a character

    oai_token-act-pair · gpt-3.5-turbo

    forms of the word "straddle" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Jinn
    -0.83
     condol
    -0.72
     sugg
    -0.68
     Noon
    -0.63
     overdue
    -0.63
     Rampage
    -0.61
     meas
    -0.60
     Reloaded
    -0.59
     nerv
    -0.56
    nih
    -0.56
    POSITIVE LOGITS
    ngth
    0.92
    upon
    0.75
    Alias
    0.74
    abo
    0.72
    atoon
    0.72
    igham
    0.70
    Goal
    0.69
     confines
    0.68
    iman
    0.67
    avid
    0.67
    Act Density 0.131%

    No Known Activations